Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.2610. Min Range: -12.2610
Max Act: 12.2610. Min Act: -0.1700
Data Index: 199327 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2610. Min Range: -12.2610
Max Act: 12.1360. Min Act: -0.1700
Data Index: 2610140 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2610. Min Range: -12.2610
Max Act: 12.1985. Min Act: -0.1700
Data Index: 4314787 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.6360. Min Act: -0.1700
Data Index: 1566278 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.7610. Min Act: -0.1700
Data Index: 3332138 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.9485. Min Act: -0.1700
Data Index: 5085799 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2610. Min Range: -12.2610
Max Act: 12.1360. Min Act: -0.1700
Data Index: 7725992 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.5735. Min Act: -0.1700
Data Index: 2306578 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.3235. Min Act: -0.1700
Data Index: 4801898 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.8860. Min Act: -0.1700
Data Index: 3712766 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.4485. Min Act: -0.1700
Data Index: 4357243 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.4485. Min Act: -0.1700
Data Index: 3058936 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.3235. Min Act: -0.1700
Data Index: 3146053 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.1360. Min Act: -0.1700
Data Index: 282389 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.0735. Min Act: -0.1700
Data Index: 7503254 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.0735. Min Act: -0.1700
Data Index: 1854913 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.1360. Min Act: -0.1700
Data Index: 2968528 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.5110. Min Act: -0.1700
Data Index: 8224476 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2610. Min Range: -12.2610
Max Act: 11.0110. Min Act: -0.1700
Data Index: 3589424 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2610. Min Range: -12.2610
Max Act: 10.9485. Min Act: -0.1700
Data Index: 5994075 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19