Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2286. Min Range: -4.2286
Max Act: 4.2286. Min Act: -0.1700
Data Index: 8342430 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8535. Min Act: -0.1700
Data Index: 1679678 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8222. Min Act: -0.1700
Data Index: 5833131 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8222. Min Act: -0.1700
Data Index: 7021273 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3374287 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3516941 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 6173684 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7440. Min Act: -0.1700
Data Index: 4629156 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7127. Min Act: -0.1700
Data Index: 8798935 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6971. Min Act: -0.1700
Data Index: 2764860 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6815. Min Act: -0.1700
Data Index: 4714039 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6345. Min Act: -0.1700
Data Index: 998820 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6189. Min Act: -0.1700
Data Index: 4677310 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6189. Min Act: -0.1700
Data Index: 1554833 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6032. Min Act: -0.1700
Data Index: 3352217 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6032. Min Act: -0.1700
Data Index: 6803213 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.5876. Min Act: -0.1700
Data Index: 5014794 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6032. Min Act: -0.1700
Data Index: 2255900 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.6032. Min Act: -0.1700
Data Index: 15198 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.5876. Min Act: -0.1700
Data Index: 4773608 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19