Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.2292. Min Act: -0.1700
Data Index: 1315653 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.2292. Min Act: -0.1700
Data Index: 5485982 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.2292. Min Act: -0.1700
Data Index: 5440125 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.2292. Min Act: -0.1698
Data Index: 2124524 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1795. Min Act: -0.1700
Data Index: 2576511 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1628. Min Act: -0.1700
Data Index: 6289892 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1628. Min Act: -0.1700
Data Index: 7627758 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1795. Min Act: -0.1700
Data Index: 3312209 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1628. Min Act: -0.1700
Data Index: 1163528 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1628. Min Act: -0.1700
Data Index: 8223639 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1295. Min Act: -0.1700
Data Index: 70231 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1295. Min Act: -0.1700
Data Index: 2761152 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1295. Min Act: -0.1700
Data Index: 635295 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1295. Min Act: -0.1700
Data Index: 194589 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1128. Min Act: -0.1700
Data Index: 3546420 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.1128. Min Act: -0.1700
Data Index: 1334185 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.0960. Min Act: -0.1700
Data Index: 4188434 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.0793. Min Act: -0.1700
Data Index: 154596 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.0960. Min Act: -0.1700
Data Index: 41607 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2292. Min Range: -2.2292
Max Act: 2.0960. Min Act: -0.1697
Data Index: 1310899 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19