Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.9323. Min Act: -0.1700
Data Index: 7221714 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.6198. Min Act: -0.1700
Data Index: 3033847 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.6198. Min Act: -0.1700
Data Index: 5705600 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.5886. Min Act: -0.1700
Data Index: 7548735 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.5261. Min Act: -0.1700
Data Index: 2949863 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4948. Min Act: -0.1700
Data Index: 4920470 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4323. Min Act: -0.1700
Data Index: 5261832 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4636. Min Act: -0.1700
Data Index: 4902419 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4636. Min Act: -0.1700
Data Index: 3417580 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4323. Min Act: -0.1700
Data Index: 307684 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4323. Min Act: -0.1700
Data Index: 7221716 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.4323. Min Act: -0.1700
Data Index: 8664322 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3698. Min Act: -0.1700
Data Index: 949017 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3386. Min Act: -0.1700
Data Index: 7746473 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3386. Min Act: -0.1700
Data Index: 5425764 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3386. Min Act: -0.1700
Data Index: 4661903 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3386. Min Act: -0.1700
Data Index: 5840710 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3386. Min Act: -0.1700
Data Index: 4374439 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3386. Min Act: -0.1700
Data Index: 2757515 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9323. Min Range: -7.9323
Max Act: 7.3073. Min Act: -0.1700
Data Index: 4673819 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19