Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1866 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.5186. Min Act: -0.1700
Data Index: 6596391 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.5186. Min Act: -0.1700
Data Index: 653106 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.4874. Min Act: -0.1700
Data Index: 2506339 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.4249. Min Act: -0.1700
Data Index: 7617345 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.4249. Min Act: -0.1700
Data Index: 8566656 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.3311. Min Act: -0.1700
Data Index: 5704499 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2999. Min Act: -0.1700
Data Index: 2713321 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2374. Min Act: -0.1700
Data Index: 537846 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2686. Min Act: -0.1700
Data Index: 1059582 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2686. Min Act: -0.1700
Data Index: 7409335 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2686. Min Act: -0.1700
Data Index: 6545969 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2374. Min Act: -0.1700
Data Index: 6829741 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2374. Min Act: -0.1700
Data Index: 488997 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2374. Min Act: -0.1700
Data Index: 3862620 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2374. Min Act: -0.1700
Data Index: 1410450 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2061. Min Act: -0.1700
Data Index: 7386279 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1749. Min Act: -0.1700
Data Index: 396213 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1749. Min Act: -0.1700
Data Index: 7791958 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1436. Min Act: -0.1700
Data Index: 156439 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1436. Min Act: -0.1700
Data Index: 1604190 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19