Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3381. Min Range: -6.3381
Max Act: 6.3381. Min Act: -0.1700
Data Index: 7897890 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3381. Min Range: -6.3381
Max Act: 6.3381. Min Act: -0.1700
Data Index: 5543282 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3381. Min Range: -6.3381
Max Act: 6.3068. Min Act: -0.1700
Data Index: 312940 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3381. Min Range: -6.3381
Max Act: 6.2131. Min Act: -0.1700
Data Index: 314744 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3381. Min Range: -6.3381
Max Act: 6.1193. Min Act: -0.1700
Data Index: 5840808 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3381. Min Range: -6.3381
Max Act: 6.0881. Min Act: -0.1700
Data Index: 4353529 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9318. Min Act: -0.1700
Data Index: 3416911 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9318. Min Act: -0.1700
Data Index: 1876234 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9631. Min Act: -0.1700
Data Index: 998139 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9006. Min Act: -0.1700
Data Index: 8480490 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9006. Min Act: -0.1700
Data Index: 8337346 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9006. Min Act: -0.1700
Data Index: 2949613 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.9006. Min Act: -0.1700
Data Index: 3075836 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.8693. Min Act: -0.1700
Data Index: 140247 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.8381. Min Act: -0.1700
Data Index: 904847 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6070061 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.7756. Min Act: -0.1700
Data Index: 685032 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.7756. Min Act: -0.1700
Data Index: 4771845 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.8068. Min Act: -0.1700
Data Index: 60146 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3381. Min Range: -6.3381
Max Act: 5.8068. Min Act: -0.1700
Data Index: 7395964 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19