Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4335 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.9773. Min Act: -0.1700
Data Index: 3934480 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.8835. Min Act: -0.1700
Data Index: 8551178 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.8210. Min Act: -0.1700
Data Index: 588984 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7898. Min Act: -0.1700
Data Index: 7158301 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7898. Min Act: -0.1700
Data Index: 7144880 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7898. Min Act: -0.1700
Data Index: 5771911 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7898. Min Act: -0.1700
Data Index: 8165028 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7585. Min Act: -0.1700
Data Index: 3226021 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7585. Min Act: -0.1700
Data Index: 887284 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7585. Min Act: -0.1700
Data Index: 7133674 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7585. Min Act: -0.1700
Data Index: 5827499 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7585. Min Act: -0.1700
Data Index: 6467253 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.7273. Min Act: -0.1700
Data Index: 8585558 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6960. Min Act: -0.1700
Data Index: 4568112 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6960. Min Act: -0.1700
Data Index: 3735382 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6960. Min Act: -0.1700
Data Index: 8240762 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6648. Min Act: -0.1700
Data Index: 7644732 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6335. Min Act: -0.1700
Data Index: 3763373 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6335. Min Act: -0.1700
Data Index: 934483 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9773. Min Range: -5.9773
Max Act: 5.6335. Min Act: -0.1700
Data Index: 4800200 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19