Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1107 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.3982. Min Act: -0.1700
Data Index: 358260 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.2732. Min Act: -0.1700
Data Index: 215003 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.2732. Min Act: -0.1700
Data Index: 4263722 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.2107. Min Act: -0.1700
Data Index: 4827709 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.1482. Min Act: -0.1700
Data Index: 4661065 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6945300 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.1170. Min Act: -0.1700
Data Index: 7231074 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0857. Min Act: -0.1700
Data Index: 6931700 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0545. Min Act: -0.1700
Data Index: 7684462 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0857. Min Act: -0.1700
Data Index: 8316810 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0545. Min Act: -0.1700
Data Index: 6074982 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0545. Min Act: -0.1700
Data Index: 5865057 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0857. Min Act: -0.1700
Data Index: 2953002 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0232. Min Act: -0.1700
Data Index: 5829626 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0232. Min Act: -0.1700
Data Index: 1797715 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0232. Min Act: -0.1700
Data Index: 8819442 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3982. Min Range: -5.3982
Max Act: 5.0545. Min Act: -0.1700
Data Index: 2228526 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9920. Min Act: -0.1700
Data Index: 3934289 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9920. Min Act: -0.1700
Data Index: 4309172 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3982. Min Range: -5.3982
Max Act: 4.9920. Min Act: -0.1700
Data Index: 1080364 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19