Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1725 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.7207. Min Act: -0.1700
Data Index: 205326 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.6894. Min Act: -0.1700
Data Index: 5975126 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.6894. Min Act: -0.1700
Data Index: 3120228 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.5957. Min Act: -0.1700
Data Index: 3641027 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.5644. Min Act: -0.1700
Data Index: 8777458 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.5332. Min Act: -0.1700
Data Index: 259754 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.5332. Min Act: -0.1700
Data Index: 7418540 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.5019. Min Act: -0.1700
Data Index: 5476913 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.4707. Min Act: -0.1700
Data Index: 6570788 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.4707. Min Act: -0.1700
Data Index: 947588 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.4707. Min Act: -0.1700
Data Index: 3060916 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.4394. Min Act: -0.1700
Data Index: 2572881 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.4394. Min Act: -0.1700
Data Index: 1944698 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.4082. Min Act: -0.1700
Data Index: 4081938 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.3769. Min Act: -0.1700
Data Index: 1796911 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.3769. Min Act: -0.1700
Data Index: 4628261 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.3769. Min Act: -0.1700
Data Index: 99352 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.3457. Min Act: -0.1700
Data Index: 2394224 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.3769. Min Act: -0.1700
Data Index: 7363075 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7207. Min Range: -6.7207
Max Act: 6.3144. Min Act: -0.1700
Data Index: 669739 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19