Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.3363. Min Act: -0.1700
Data Index: 6790422 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.3050. Min Act: -0.1700
Data Index: 3565877 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.2113. Min Act: -0.1700
Data Index: 7013979 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.2425. Min Act: -0.1700
Data Index: 6628983 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1800. Min Act: -0.1700
Data Index: 897694 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1488. Min Act: -0.1700
Data Index: 3564805 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1488. Min Act: -0.1700
Data Index: 4069313 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1800. Min Act: -0.1700
Data Index: 2920125 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1488. Min Act: -0.1700
Data Index: 2753099 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1488. Min Act: -0.1700
Data Index: 5965609 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1488. Min Act: -0.1700
Data Index: 3668294 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1800. Min Act: -0.1700
Data Index: 8431056 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1488. Min Act: -0.1700
Data Index: 3071782 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1700
Data Index: 6585879 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1700
Data Index: 2847044 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1699
Data Index: 79283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1700
Data Index: 4329113 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1700
Data Index: 1180689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1700
Data Index: 1703671 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3363. Min Range: -5.3363
Max Act: 5.1175. Min Act: -0.1700
Data Index: 955029 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19