Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2050. Min Range: -6.2050
Max Act: 6.2050. Min Act: -0.1700
Data Index: 7715006 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2050. Min Range: -6.2050
Max Act: 6.0487. Min Act: -0.1700
Data Index: 1087452 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2050. Min Range: -6.2050
Max Act: 6.1112. Min Act: -0.1700
Data Index: 1110058 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2050. Min Range: -6.2050
Max Act: 6.0175. Min Act: -0.1700
Data Index: 1615692 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.9237. Min Act: -0.1700
Data Index: 7946810 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.8925. Min Act: -0.1700
Data Index: 6821055 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7675. Min Act: -0.1700
Data Index: 4924104 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7675. Min Act: -0.1700
Data Index: 4694028 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7675. Min Act: -0.1700
Data Index: 2842239 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7987. Min Act: -0.1700
Data Index: 4541160 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7675. Min Act: -0.1700
Data Index: 1134124 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7675. Min Act: -0.1700
Data Index: 8503854 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7362. Min Act: -0.1700
Data Index: 7897627 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7050. Min Act: -0.1700
Data Index: 8629343 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7362. Min Act: -0.1700
Data Index: 7917795 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7050. Min Act: -0.1700
Data Index: 2691341 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.6425. Min Act: -0.1700
Data Index: 2079994 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6170012 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7362. Min Act: -0.1700
Data Index: 1538072 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2050. Min Range: -6.2050
Max Act: 5.7050. Min Act: -0.1700
Data Index: 7190886 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19