Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 763 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.9598. Min Act: -0.1700
Data Index: 8087847 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.9286. Min Act: -0.1700
Data Index: 7040854 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1184079 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.8973. Min Act: -0.1700
Data Index: 2744503 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.8348. Min Act: -0.1700
Data Index: 8720705 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.8348. Min Act: -0.1700
Data Index: 574573 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.8348. Min Act: -0.1700
Data Index: 3157681 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7411. Min Act: -0.1700
Data Index: 6920163 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7723. Min Act: -0.1700
Data Index: 3945748 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7723. Min Act: -0.1700
Data Index: 7188086 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7471795 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7411. Min Act: -0.1700
Data Index: 8554982 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7411. Min Act: -0.1700
Data Index: 5282349 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7264178 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 1815590 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 5114379 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 4129016 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2053518 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 169776 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9598. Min Range: -5.9598
Max Act: 5.7098. Min Act: -0.1700
Data Index: 3751907 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19