Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5337 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.3332. Min Act: -0.1700
Data Index: 898431 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.3168. Min Act: -0.1700
Data Index: 6778453 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2509. Min Act: -0.1700
Data Index: 8652903 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2509. Min Act: -0.1700
Data Index: 3040970 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2344. Min Act: -0.1700
Data Index: 6703631 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2344. Min Act: -0.1700
Data Index: 2128322 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2344. Min Act: -0.1700
Data Index: 8301457 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2344. Min Act: -0.1700
Data Index: 129770 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2013. Min Act: -0.1700
Data Index: 5711840 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2178. Min Act: -0.1700
Data Index: 6076999 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2178. Min Act: -0.1700
Data Index: 6984883 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2344. Min Act: -0.1700
Data Index: 2156140 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2178. Min Act: -0.1700
Data Index: 3042831 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.2013. Min Act: -0.1700
Data Index: 2534423 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.1846. Min Act: -0.1700
Data Index: 4902582 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.1846. Min Act: -0.1700
Data Index: 246768 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.1846. Min Act: -0.1700
Data Index: 4409524 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.1680. Min Act: -0.1700
Data Index: 5406659 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.1846. Min Act: -0.1700
Data Index: 5484942 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3332. Min Range: -2.3332
Max Act: 2.1846. Min Act: -0.1700
Data Index: 3121000 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19