Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2181. Min Range: -6.2181
Max Act: 6.2181. Min Act: -0.1696
Data Index: 5100714 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2181. Min Range: -6.2181
Max Act: 6.0306. Min Act: -0.1700
Data Index: 5376046 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.9368. Min Act: -0.1700
Data Index: 1739558 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.9368. Min Act: -0.1700
Data Index: 8726721 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.8743. Min Act: -0.1700
Data Index: 2192893 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.7806. Min Act: -0.1700
Data Index: 2765019 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.7493. Min Act: -0.1700
Data Index: 6531202 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.7181. Min Act: -0.1700
Data Index: 3565291 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6868. Min Act: -0.1700
Data Index: 5225278 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.7493. Min Act: -0.1700
Data Index: 1850321 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6868. Min Act: -0.1700
Data Index: 2655613 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6868. Min Act: -0.1700
Data Index: 1669956 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6556. Min Act: -0.1700
Data Index: 5666499 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6868. Min Act: -0.1700
Data Index: 6898572 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6556. Min Act: -0.1700
Data Index: 1136923 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6243. Min Act: -0.1700
Data Index: 731828 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.5931. Min Act: -0.1700
Data Index: 4927659 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6243. Min Act: -0.1700
Data Index: 876554 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6243. Min Act: -0.1700
Data Index: 1183089 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2181. Min Range: -6.2181
Max Act: 5.6243. Min Act: -0.1700
Data Index: 224251 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19