Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.5072. Min Act: -0.1700
Data Index: 452662 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.4760. Min Act: -0.1700
Data Index: 3286657 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.4447. Min Act: -0.1700
Data Index: 5478724 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.5072. Min Act: -0.1700
Data Index: 5550958 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.4760. Min Act: -0.1700
Data Index: 5594561 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.2885. Min Act: -0.1700
Data Index: 4618364 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.2572. Min Act: -0.1700
Data Index: 827665 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.2572. Min Act: -0.1700
Data Index: 1707981 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1947. Min Act: -0.1700
Data Index: 3054434 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1635. Min Act: -0.1700
Data Index: 7271727 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1322. Min Act: -0.1700
Data Index: 5970367 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1322. Min Act: -0.1700
Data Index: 2182 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1322. Min Act: -0.1700
Data Index: 69635 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1322. Min Act: -0.1700
Data Index: 7167644 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1010. Min Act: -0.1700
Data Index: 7073219 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.1010. Min Act: -0.1700
Data Index: 6330637 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.0697. Min Act: -0.1700
Data Index: 894027 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.0697. Min Act: -0.1700
Data Index: 8592799 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.0385. Min Act: -0.1700
Data Index: 6891872 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5072. Min Range: -6.5072
Max Act: 6.0385. Min Act: -0.1700
Data Index: 8736988 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19