Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1260. Min Range: -5.1260
Max Act: 5.1260. Min Act: -0.1700
Data Index: 4475931 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9697. Min Act: -0.1700
Data Index: 5557320 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9697. Min Act: -0.1700
Data Index: 5034614 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9697. Min Act: -0.1700
Data Index: 5731699 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9697. Min Act: -0.1700
Data Index: 6428729 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9385. Min Act: -0.1700
Data Index: 6554585 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9385. Min Act: -0.1700
Data Index: 4221159 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9697. Min Act: -0.1700
Data Index: 1549471 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9385. Min Act: -0.1700
Data Index: 5880333 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9385. Min Act: -0.1700
Data Index: 5389666 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 4565719 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 4742866 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9385. Min Act: -0.1700
Data Index: 2662259 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 4361082 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 3331092 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 5226846 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 8710051 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.9072. Min Act: -0.1700
Data Index: 5660017 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.8760. Min Act: -0.1700
Data Index: 3605948 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1260. Min Range: -5.1260
Max Act: 4.8760. Min Act: -0.1700
Data Index: 6524799 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19