Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.2133. Min Act: -0.1700
Data Index: 2571705 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.1818. Min Act: -0.1700
Data Index: 4303065 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.1503. Min Act: -0.1700
Data Index: 635519 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.0242. Min Act: -0.1700
Data Index: 7879643 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.0242. Min Act: -0.1700
Data Index: 1621917 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9610. Min Act: -0.1700
Data Index: 1122973 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9451. Min Act: -0.1700
Data Index: 4303066 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9135. Min Act: -0.1700
Data Index: 7504984 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9135. Min Act: -0.1700
Data Index: 1405103 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9135. Min Act: -0.1700
Data Index: 6173625 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8817. Min Act: -0.1700
Data Index: 810443 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8817. Min Act: -0.1700
Data Index: 3314508 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8817. Min Act: -0.1700
Data Index: 6199001 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8817. Min Act: -0.1700
Data Index: 6243904 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8500. Min Act: -0.1700
Data Index: 6215139 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8500. Min Act: -0.1700
Data Index: 4833384 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8341. Min Act: -0.1700
Data Index: 3416728 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8341. Min Act: -0.1700
Data Index: 1504021 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8341. Min Act: -0.1700
Data Index: 3285936 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8182. Min Act: -0.1700
Data Index: 7479979 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19