Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0460. Min Range: -3.0460
Max Act: 3.0460. Min Act: -0.1700
Data Index: 8448404 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.9195. Min Act: -0.1700
Data Index: 2042023 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.9037. Min Act: -0.1700
Data Index: 500775 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8878. Min Act: -0.1700
Data Index: 2973949 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8719. Min Act: -0.1700
Data Index: 1463537 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8560. Min Act: -0.1700
Data Index: 5885985 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8401. Min Act: -0.1700
Data Index: 7132205 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8401. Min Act: -0.1700
Data Index: 275728 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8242. Min Act: -0.1700
Data Index: 6989734 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8083. Min Act: -0.1700
Data Index: 3243733 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8242. Min Act: -0.1700
Data Index: 2048816 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.7924. Min Act: -0.1700
Data Index: 290405 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.7924. Min Act: -0.1700
Data Index: 421446 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8242. Min Act: -0.1700
Data Index: 5000172 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8083. Min Act: -0.1700
Data Index: 4678848 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.8083. Min Act: -0.1700
Data Index: 6471331 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.7924. Min Act: -0.1700
Data Index: 8460434 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.7765. Min Act: -0.1700
Data Index: 8020479 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.7924. Min Act: -0.1700
Data Index: 5498110 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0460. Min Range: -3.0460
Max Act: 2.7765. Min Act: -0.1700
Data Index: 4694382 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19