Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.4235. Min Act: -0.1700
Data Index: 7325973 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.4860. Min Act: -0.1700
Data Index: 7910959 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.4860. Min Act: -0.1700
Data Index: 6451658 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.4235. Min Act: -0.1700
Data Index: 2345250 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.2985. Min Act: -0.1700
Data Index: 2598062 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.2985. Min Act: -0.1700
Data Index: 1266959 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.2672. Min Act: -0.1700
Data Index: 1118288 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1735. Min Act: -0.1700
Data Index: 8792149 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1735. Min Act: -0.1700
Data Index: 7048762 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.2047. Min Act: -0.1700
Data Index: 889462 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1110. Min Act: -0.1700
Data Index: 6165581 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1422. Min Act: -0.1700
Data Index: 5423234 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.0797. Min Act: -0.1700
Data Index: 7325972 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1422. Min Act: -0.1700
Data Index: 1676004 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.0797. Min Act: -0.1700
Data Index: 4463201 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1110. Min Act: -0.1700
Data Index: 2564653 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1110. Min Act: -0.1700
Data Index: 6579660 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.1110. Min Act: -0.1700
Data Index: 5850681 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.0797. Min Act: -0.1700
Data Index: 4328865 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4860. Min Range: -8.4860
Max Act: 8.0797. Min Act: -0.1700
Data Index: 883535 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19