Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0181. Min Range: -8.0181
Max Act: 8.0181. Min Act: -0.1700
Data Index: 4042733 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0181. Min Range: -8.0181
Max Act: 8.0181. Min Act: -0.1700
Data Index: 5056324 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.7681. Min Act: -0.1700
Data Index: 7287040 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6744. Min Act: -0.1700
Data Index: 6462500 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.7994. Min Act: -0.1700
Data Index: 41596 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.7994. Min Act: -0.1700
Data Index: 6324360 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.7056. Min Act: -0.1700
Data Index: 6462498 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.7994. Min Act: -0.1700
Data Index: 5399531 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6744. Min Act: -0.1700
Data Index: 6550708 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6744. Min Act: -0.1700
Data Index: 387125 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6744. Min Act: -0.1700
Data Index: 5426847 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6744. Min Act: -0.1700
Data Index: 6329390 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6744. Min Act: -0.1700
Data Index: 5450206 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1699
Data Index: 3832528 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1700
Data Index: 898636 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1700
Data Index: 1869015 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1700
Data Index: 5923098 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1700
Data Index: 324747 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1700
Data Index: 787792 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0181. Min Range: -8.0181
Max Act: 7.6431. Min Act: -0.1700
Data Index: 1759159 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19