Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4248 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.3876. Min Act: -0.1700
Data Index: 3074636 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.3248. Min Act: -0.1700
Data Index: 4414538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.3405. Min Act: -0.1700
Data Index: 3178334 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.3248. Min Act: -0.1700
Data Index: 918016 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2149. Min Act: -0.1700
Data Index: 1181843 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2306. Min Act: -0.1700
Data Index: 3804604 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2463. Min Act: -0.1700
Data Index: 7496647 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2306. Min Act: -0.1700
Data Index: 1241539 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1991. Min Act: -0.1700
Data Index: 374170 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2149. Min Act: -0.1700
Data Index: 4421235 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2149. Min Act: -0.1700
Data Index: 7947644 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1991. Min Act: -0.1700
Data Index: 4488809 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.2463. Min Act: -0.1700
Data Index: 2292701 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1991. Min Act: -0.1700
Data Index: 671309 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1991. Min Act: -0.1700
Data Index: 6772985 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1834. Min Act: -0.1700
Data Index: 3987606 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1834. Min Act: -0.1700
Data Index: 318116 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1677. Min Act: -0.1700
Data Index: 7884186 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1677. Min Act: -0.1700
Data Index: 59585 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3876. Min Range: -3.3876
Max Act: 3.1834. Min Act: -0.1700
Data Index: 3224022 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19