Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 7008156 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8868. Min Act: -0.1700
Data Index: 7008157 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7931. Min Act: -0.1700
Data Index: 4142162 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6368. Min Act: -0.1700
Data Index: 1942990 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 6183197 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 4574710 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5430. Min Act: -0.1700
Data Index: 6294658 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4805. Min Act: -0.1700
Data Index: 3830287 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5118. Min Act: -0.1700
Data Index: 863063 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4805. Min Act: -0.1700
Data Index: 7216994 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4805. Min Act: -0.1700
Data Index: 1295582 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4805. Min Act: -0.1700
Data Index: 7688868 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4805. Min Act: -0.1700
Data Index: 5547466 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4493. Min Act: -0.1700
Data Index: 3037427 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4493. Min Act: -0.1700
Data Index: 4284735 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4493. Min Act: -0.1700
Data Index: 5943920 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4493. Min Act: -0.1700
Data Index: 8786003 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4493. Min Act: -0.1700
Data Index: 4792514 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4180. Min Act: -0.1699
Data Index: 1863291 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.4180. Min Act: -0.1700
Data Index: 4174012 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19