Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3655. Min Range: -6.3655
Max Act: 6.3655. Min Act: -0.1700
Data Index: 6142817 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.9280. Min Act: -0.1700
Data Index: 4464301 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.8967. Min Act: -0.1700
Data Index: 2772244 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.7092. Min Act: -0.1700
Data Index: 585227 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4586458 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.6780. Min Act: -0.1700
Data Index: 5304395 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.6155. Min Act: -0.1700
Data Index: 3487277 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.6467. Min Act: -0.1700
Data Index: 832644 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 3175807 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 4561896 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 3086503 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 2747852 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 593855 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5530. Min Act: -0.1700
Data Index: 7809990 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5217. Min Act: -0.1700
Data Index: 5254363 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.5217. Min Act: -0.1700
Data Index: 7923301 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.4592. Min Act: -0.1700
Data Index: 6840935 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.4905. Min Act: -0.1700
Data Index: 1245690 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.4905. Min Act: -0.1700
Data Index: 141235 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3655. Min Range: -6.3655
Max Act: 5.4905. Min Act: -0.1700
Data Index: 673596 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19