Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.3742. Min Act: -0.1700
Data Index: 7180721 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.3117. Min Act: -0.1700
Data Index: 210997 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.3117. Min Act: -0.1700
Data Index: 6471064 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.2180. Min Act: -0.1700
Data Index: 5244220 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1867. Min Act: -0.1700
Data Index: 7131324 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1242. Min Act: -0.1700
Data Index: 2750775 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1555. Min Act: -0.1700
Data Index: 5252124 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1867. Min Act: -0.1700
Data Index: 2680301 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1242. Min Act: -0.1700
Data Index: 6432563 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1242. Min Act: -0.1700
Data Index: 7862817 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1242. Min Act: -0.1700
Data Index: 2134340 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.1242. Min Act: -0.1700
Data Index: 479652 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0930. Min Act: -0.1700
Data Index: 1772295 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0930. Min Act: -0.1700
Data Index: 4468477 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0930. Min Act: -0.1700
Data Index: 7081907 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0617. Min Act: -0.1700
Data Index: 7005946 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0305. Min Act: -0.1700
Data Index: 6814089 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0305. Min Act: -0.1700
Data Index: 6753709 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3742. Min Range: -6.3742
Max Act: 5.9992. Min Act: -0.1700
Data Index: 2244281 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3742. Min Range: -6.3742
Max Act: 6.0305. Min Act: -0.1700
Data Index: 2731494 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19