Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5952 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.9566. Min Act: -0.1700
Data Index: 1457317 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.8941. Min Act: -0.1700
Data Index: 7691232 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.8941. Min Act: -0.1700
Data Index: 5485143 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.7066. Min Act: -0.1700
Data Index: 4912871 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.7066. Min Act: -0.1700
Data Index: 560146 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.7066. Min Act: -0.1700
Data Index: 5799565 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.7066. Min Act: -0.1700
Data Index: 995315 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.6441. Min Act: -0.1700
Data Index: 2421677 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.6441. Min Act: -0.1700
Data Index: 1820192 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.5816. Min Act: -0.1700
Data Index: 5433116 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.5191. Min Act: -0.1700
Data Index: 3182760 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.5191. Min Act: -0.1700
Data Index: 7705363 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.4879. Min Act: -0.1700
Data Index: 1888716 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.4566. Min Act: -0.1700
Data Index: 588722 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.4254. Min Act: -0.1700
Data Index: 6127545 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.3629. Min Act: -0.1700
Data Index: 352873 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.3629. Min Act: -0.1700
Data Index: 3903210 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.3316. Min Act: -0.1700
Data Index: 1214998 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.2691. Min Act: -0.1700
Data Index: 6517429 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9566. Min Range: -7.9566
Max Act: 7.2379. Min Act: -0.1700
Data Index: 7665985 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19