Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.6673. Min Act: -0.1700
Data Index: 2811613 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.6048. Min Act: -0.1700
Data Index: 6419977 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.5735. Min Act: -0.1700
Data Index: 4484984 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.4485. Min Act: -0.1700
Data Index: 775093 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.4485. Min Act: -0.1700
Data Index: 3281931 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.4173. Min Act: -0.1700
Data Index: 7109904 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.4173. Min Act: -0.1700
Data Index: 7109906 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.4173. Min Act: -0.1700
Data Index: 1287096 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.3860. Min Act: -0.1700
Data Index: 401862 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.3548. Min Act: -0.1700
Data Index: 85715 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.3235. Min Act: -0.1700
Data Index: 6283241 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.3235. Min Act: -0.1700
Data Index: 1674615 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.2923. Min Act: -0.1700
Data Index: 4200575 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.2923. Min Act: -0.1700
Data Index: 6283242 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5859243 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.1985. Min Act: -0.1700
Data Index: 8573227 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.1985. Min Act: -0.1700
Data Index: 2350549 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.1360. Min Act: -0.1700
Data Index: 7431167 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.1673. Min Act: -0.1700
Data Index: 2945954 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6673. Min Range: -5.6673
Max Act: 5.1048. Min Act: -0.1700
Data Index: 7732134 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19