Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8484. Min Act: -0.1700
Data Index: 6070592 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8484. Min Act: -0.1700
Data Index: 1059480 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8398. Min Act: -0.1700
Data Index: 5438844 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8313. Min Act: -0.1700
Data Index: 5028635 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8313. Min Act: -0.1700
Data Index: 8394994 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8313. Min Act: -0.1700
Data Index: 7753159 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8227. Min Act: -0.1700
Data Index: 7220226 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8227. Min Act: -0.1700
Data Index: 6653372 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8055. Min Act: -0.1699
Data Index: 4464292 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8141. Min Act: -0.1697
Data Index: 6746438 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.8055. Min Act: -0.1700
Data Index: 2456932 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7883. Min Act: -0.1700
Data Index: 8406936 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7883. Min Act: -0.1700
Data Index: 1169793 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7883. Min Act: -0.1700
Data Index: 7132551 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7711. Min Act: -0.1700
Data Index: 7637005 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7624. Min Act: -0.1700
Data Index: 5028634 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7711. Min Act: -0.1700
Data Index: 6770030 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7711. Min Act: -0.1700
Data Index: 6490873 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7624. Min Act: -0.1700
Data Index: 6519347 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8484. Min Range: -1.8484
Max Act: 1.7538. Min Act: -0.1700
Data Index: 7600478 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19