Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0906. Min Act: -0.1700
Data Index: 3513366 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0739. Min Act: -0.1700
Data Index: 8042706 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0065. Min Act: -0.1700
Data Index: 7258172 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0402. Min Act: -0.1700
Data Index: 4016866 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0234. Min Act: -0.1700
Data Index: 7658027 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0402. Min Act: -0.1700
Data Index: 260862 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9896. Min Act: -0.1700
Data Index: 3741335 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9812. Min Act: -0.1700
Data Index: 2582266 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9896. Min Act: -0.1700
Data Index: 1078713 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9896. Min Act: -0.1700
Data Index: 2199210 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0234. Min Act: -0.1700
Data Index: 6501659 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0906. Min Range: -2.0906
Max Act: 2.0065. Min Act: -0.1699
Data Index: 3974067 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9896. Min Act: -0.1700
Data Index: 8143062 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9896. Min Act: -0.1700
Data Index: 3840105 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9812. Min Act: -0.1700
Data Index: 7218564 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9642. Min Act: -0.1700
Data Index: 7366524 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9812. Min Act: -0.1700
Data Index: 1542022 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9812. Min Act: -0.1700
Data Index: 790803 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9557. Min Act: -0.1699
Data Index: 8349445 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0906. Min Range: -2.0906
Max Act: 1.9557. Min Act: -0.1700
Data Index: 1063508 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19