Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.5112. Min Act: -0.1700
Data Index: 3044289 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 6396304 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 6765037 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 368841 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 3318784 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2596154 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4175. Min Act: -0.1700
Data Index: 966608 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 1932879 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 1436607 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 1997273 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 4996165 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 3377207 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2085068 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3237. Min Act: -0.1700
Data Index: 2167989 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 3824102 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3237. Min Act: -0.1700
Data Index: 5906781 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3550. Min Act: -0.1700
Data Index: 3166581 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3550. Min Act: -0.1700
Data Index: 6217438 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3550. Min Act: -0.1700
Data Index: 6464560 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3550. Min Act: -0.1700
Data Index: 1886475 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19