Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 793 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1820. Min Range: -10.1820
Max Act: 10.1820. Min Act: -0.1700
Data Index: 5676777 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1820. Min Range: -10.1820
Max Act: 10.1195. Min Act: -0.1700
Data Index: 8147121 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1820. Min Range: -10.1820
Max Act: 10.0570. Min Act: -0.1700
Data Index: 2949212 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.9945. Min Act: -0.1700
Data Index: 5950021 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.9945. Min Act: -0.1700
Data Index: 8458498 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.9320. Min Act: -0.1700
Data Index: 8036932 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.8695. Min Act: -0.1700
Data Index: 1912049 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.8695. Min Act: -0.1700
Data Index: 1547572 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.8070. Min Act: -0.1700
Data Index: 8802744 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.8070. Min Act: -0.1700
Data Index: 4814582 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 2561048 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 6620567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 2190113 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 6532415 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 7314986 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 3800102 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.7445. Min Act: -0.1700
Data Index: 2748819 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.6820. Min Act: -0.1700
Data Index: 5581026 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.6820. Min Act: -0.1700
Data Index: 1511461 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1820. Min Range: -10.1820
Max Act: 9.6820. Min Act: -0.1700
Data Index: 2248143 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19