Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 911 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0322. Min Range: -6.0322
Max Act: 6.0322. Min Act: -0.1700
Data Index: 3091342 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.9697. Min Act: -0.1700
Data Index: 1474431 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8760. Min Act: -0.1700
Data Index: 5246931 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8760. Min Act: -0.1700
Data Index: 7315669 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.9072. Min Act: -0.1700
Data Index: 3616050 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8760. Min Act: -0.1700
Data Index: 2088466 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8760. Min Act: -0.1700
Data Index: 3312310 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8447. Min Act: -0.1700
Data Index: 6988057 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5618384 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 4672717 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8135. Min Act: -0.1700
Data Index: 1288077 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8135. Min Act: -0.1700
Data Index: 3902592 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4449520 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6882015 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 21352 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7510. Min Act: -0.1700
Data Index: 2733658 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 7756420 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 286886 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 7372226 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0322. Min Range: -6.0322
Max Act: 5.7822. Min Act: -0.1700
Data Index: 7072543 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19