Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3141 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.8373. Min Act: -0.1700
Data Index: 3933709 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7896. Min Act: -0.1700
Data Index: 6514493 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.8055. Min Act: -0.1700
Data Index: 6008127 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7417. Min Act: -0.1700
Data Index: 8485082 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7098. Min Act: -0.1700
Data Index: 3350691 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6777. Min Act: -0.1700
Data Index: 4164200 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7417. Min Act: -0.1700
Data Index: 5433826 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7258. Min Act: -0.1700
Data Index: 1483976 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7258. Min Act: -0.1700
Data Index: 7255532 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6938. Min Act: -0.1700
Data Index: 5573418 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6777. Min Act: -0.1700
Data Index: 4512141 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7098. Min Act: -0.1700
Data Index: 3167336 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6777. Min Act: -0.1700
Data Index: 980220 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6777. Min Act: -0.1700
Data Index: 5627998 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6938. Min Act: -0.1700
Data Index: 8377262 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6457. Min Act: -0.1700
Data Index: 2046236 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6938. Min Act: -0.1700
Data Index: 8203771 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6617. Min Act: -0.1700
Data Index: 3938213 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.6777. Min Act: -0.1700
Data Index: 2915406 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8373. Min Range: -2.8373
Max Act: 2.7098. Min Act: -0.1700
Data Index: 6832490 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19