Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3719 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.6717. Min Act: -0.1700
Data Index: 6914400 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.6092. Min Act: -0.1700
Data Index: 2307437 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.5779. Min Act: -0.1700
Data Index: 6105747 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.5467. Min Act: -0.1700
Data Index: 1603211 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.4842. Min Act: -0.1700
Data Index: 7861902 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.4529. Min Act: -0.1700
Data Index: 4202344 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.4217. Min Act: -0.1700
Data Index: 213364 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.4217. Min Act: -0.1700
Data Index: 6782503 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.3592. Min Act: -0.1700
Data Index: 2754232 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.3592. Min Act: -0.1700
Data Index: 6947820 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2967. Min Act: -0.1700
Data Index: 1819387 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2967. Min Act: -0.1700
Data Index: 5085033 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2967. Min Act: -0.1700
Data Index: 808132 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2342. Min Act: -0.1700
Data Index: 4021828 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2342. Min Act: -0.1700
Data Index: 2482518 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2029. Min Act: -0.1700
Data Index: 5271069 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2029. Min Act: -0.1700
Data Index: 8804554 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.2029. Min Act: -0.1700
Data Index: 3597777 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.1717. Min Act: -0.1700
Data Index: 855956 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6717. Min Range: -7.6717
Max Act: 7.1717. Min Act: -0.1700
Data Index: 541260 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19