Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.2992. Min Act: -0.1700
Data Index: 8636217 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.2680. Min Act: -0.1700
Data Index: 4680002 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8617. Min Act: -0.1700
Data Index: 2071747 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8930. Min Act: -0.1700
Data Index: 5829246 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8305. Min Act: -0.1700
Data Index: 2216990 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8305. Min Act: -0.1700
Data Index: 5369749 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7055. Min Act: -0.1700
Data Index: 2516807 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6742. Min Act: -0.1700
Data Index: 4074551 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7055. Min Act: -0.1700
Data Index: 7931338 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.7055. Min Act: -0.1700
Data Index: 8330452 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6430. Min Act: -0.1700
Data Index: 556028 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6742. Min Act: -0.1700
Data Index: 7167907 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6430. Min Act: -0.1700
Data Index: 8794660 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6117. Min Act: -0.1700
Data Index: 1698801 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.6117. Min Act: -0.1700
Data Index: 6396380 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.5492. Min Act: -0.1700
Data Index: 2607035 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.5805. Min Act: -0.1700
Data Index: 2619240 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.5180. Min Act: -0.1700
Data Index: 5227905 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.5492. Min Act: -0.1700
Data Index: 2288765 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.4867. Min Act: -0.1700
Data Index: 3384969 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19