Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4644 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.5396. Min Act: -0.1700
Data Index: 4210769 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.3834. Min Act: -0.1700
Data Index: 946500 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.3209. Min Act: -0.1700
Data Index: 8236218 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.3209. Min Act: -0.1700
Data Index: 1980321 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2896. Min Act: -0.1700
Data Index: 5237563 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2896. Min Act: -0.1700
Data Index: 272890 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2584. Min Act: -0.1700
Data Index: 2668052 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2584. Min Act: -0.1700
Data Index: 3643543 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2584. Min Act: -0.1700
Data Index: 5761744 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2584. Min Act: -0.1700
Data Index: 7836478 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2271. Min Act: -0.1700
Data Index: 1945858 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2271. Min Act: -0.1700
Data Index: 6945991 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2271. Min Act: -0.1700
Data Index: 272892 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2271. Min Act: -0.1700
Data Index: 1322475 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.2271. Min Act: -0.1700
Data Index: 7689668 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.1959. Min Act: -0.1700
Data Index: 652264 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.1959. Min Act: -0.1700
Data Index: 8453088 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.1646. Min Act: -0.1700
Data Index: 7430407 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.1646. Min Act: -0.1700
Data Index: 3299178 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5396. Min Range: -4.5396
Max Act: 4.1646. Min Act: -0.1700
Data Index: 4104983 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19