Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.9072. Min Act: -0.1700
Data Index: 3145435 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.8134. Min Act: -0.1700
Data Index: 959294 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.8134. Min Act: -0.1700
Data Index: 6088298 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.7195. Min Act: -0.1700
Data Index: 389822 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.7195. Min Act: -0.1700
Data Index: 2899736 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6882. Min Act: -0.1700
Data Index: 3145434 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6882. Min Act: -0.1700
Data Index: 5383106 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6882. Min Act: -0.1700
Data Index: 2970823 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6569. Min Act: -0.1700
Data Index: 927290 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6569. Min Act: -0.1700
Data Index: 7386875 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6569. Min Act: -0.1700
Data Index: 7589767 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6257. Min Act: -0.1700
Data Index: 3647245 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 4570136 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.6257. Min Act: -0.1700
Data Index: 4019790 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 4096286 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 1539053 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 1074280 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 3831248 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 3849933 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9072. Min Range: -3.9072
Max Act: 3.5944. Min Act: -0.1700
Data Index: 789505 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19