Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1520 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.6332. Min Act: -0.1700
Data Index: 3415926 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.5707. Min Act: -0.1700
Data Index: 3002081 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.5707. Min Act: -0.1700
Data Index: 2014609 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.5082. Min Act: -0.1700
Data Index: 6037205 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.4457. Min Act: -0.1700
Data Index: 7632171 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.4457. Min Act: -0.1700
Data Index: 3423719 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.4145. Min Act: -0.1700
Data Index: 3301810 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.4145. Min Act: -0.1700
Data Index: 4673642 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.4145. Min Act: -0.1700
Data Index: 2500910 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3832. Min Act: -0.1700
Data Index: 789393 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3832. Min Act: -0.1700
Data Index: 4145949 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3832. Min Act: -0.1700
Data Index: 6750909 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3520. Min Act: -0.1700
Data Index: 105439 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3520. Min Act: -0.1700
Data Index: 1682563 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3520. Min Act: -0.1700
Data Index: 1059495 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3520. Min Act: -0.1700
Data Index: 1411954 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3207. Min Act: -0.1700
Data Index: 3301812 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3207. Min Act: -0.1700
Data Index: 3312779 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3207. Min Act: -0.1700
Data Index: 3288143 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6332. Min Range: -5.6332
Max Act: 5.3207. Min Act: -0.1700
Data Index: 2354547 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19