Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1766 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2348. Min Act: -0.1700
Data Index: 1177904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2348. Min Act: -0.1700
Data Index: 5750334 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 1665401 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 7691560 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.1719. Min Act: -0.1700
Data Index: 7231522 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 1081414 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 6706765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 6444357 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 6219097 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 5661003 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 5661000 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 3495002 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 882922 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 1357903 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 460360 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 1320719 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 5298386 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.1719. Min Act: -0.1700
Data Index: 5038297 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 4596357 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2348. Min Range: -3.2348
Max Act: 3.2034. Min Act: -0.1700
Data Index: 3543940 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19