Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6170 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.6756. Min Act: -0.1700
Data Index: 7187044 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.5506. Min Act: -0.1700
Data Index: 978905 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.5506. Min Act: -0.1700
Data Index: 8503407 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.5193. Min Act: -0.1700
Data Index: 8378344 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.4881. Min Act: -0.1700
Data Index: 4719379 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.4568. Min Act: -0.1700
Data Index: 455399 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.4256. Min Act: -0.1700
Data Index: 5019153 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.4256. Min Act: -0.1700
Data Index: 6278441 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3943. Min Act: -0.1700
Data Index: 8166508 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3631. Min Act: -0.1700
Data Index: 6501928 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3318. Min Act: -0.1700
Data Index: 7187046 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3631. Min Act: -0.1700
Data Index: 5968042 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3006. Min Act: -0.1700
Data Index: 8183287 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3006. Min Act: -0.1700
Data Index: 6370575 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3006. Min Act: -0.1700
Data Index: 2739500 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.2693. Min Act: -0.1700
Data Index: 4933432 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.3006. Min Act: -0.1700
Data Index: 2840548 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6246186 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.2381. Min Act: -0.1700
Data Index: 2532617 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6756. Min Range: -5.6756
Max Act: 5.2381. Min Act: -0.1700
Data Index: 500774 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19