Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.9881. Min Act: -0.1700
Data Index: 7687737 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.9569. Min Act: -0.1700
Data Index: 5072404 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.9256. Min Act: -0.1700
Data Index: 7319828 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8631. Min Act: -0.1700
Data Index: 8517725 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8318. Min Act: -0.1700
Data Index: 2970542 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8318. Min Act: -0.1700
Data Index: 8533490 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7693. Min Act: -0.1700
Data Index: 833377 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8005. Min Act: -0.1700
Data Index: 4596500 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8005. Min Act: -0.1700
Data Index: 5287008 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8005. Min Act: -0.1700
Data Index: 1548473 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7693. Min Act: -0.1700
Data Index: 8719611 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7693. Min Act: -0.1700
Data Index: 3239742 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7693. Min Act: -0.1700
Data Index: 2442578 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.8005. Min Act: -0.1700
Data Index: 7995967 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7693. Min Act: -0.1700
Data Index: 2930807 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7380. Min Act: -0.1700
Data Index: 5894658 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7380. Min Act: -0.1700
Data Index: 1845441 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7380. Min Act: -0.1700
Data Index: 3387668 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7380. Min Act: -0.1700
Data Index: 5123080 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9881. Min Range: -3.9881
Max Act: 3.7380. Min Act: -0.1700
Data Index: 2553630 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19