Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 222 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1473. Min Range: -9.1473
Max Act: 9.1473. Min Act: -0.1700
Data Index: 4499101 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.8348. Min Act: -0.1700
Data Index: 4687380 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.8348. Min Act: -0.1700
Data Index: 5917601 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.7723. Min Act: -0.1700
Data Index: 4096984 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.4598. Min Act: -0.1700
Data Index: 4826383 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.4598. Min Act: -0.1700
Data Index: 261570 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.3973. Min Act: -0.1700
Data Index: 1899603 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.3973. Min Act: -0.1700
Data Index: 895148 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.3348. Min Act: -0.1700
Data Index: 2534245 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.3348. Min Act: -0.1700
Data Index: 4120758 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2723. Min Act: -0.1700
Data Index: 3359000 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2723. Min Act: -0.1700
Data Index: 1429501 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2723. Min Act: -0.1700
Data Index: 3606773 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2723. Min Act: -0.1700
Data Index: 4028999 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2723. Min Act: -0.1700
Data Index: 7119296 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2723. Min Act: -0.1700
Data Index: 6961611 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2098. Min Act: -0.1700
Data Index: 3278004 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.1473. Min Act: -0.1700
Data Index: 4485043 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2098. Min Act: -0.1700
Data Index: 757528 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1473. Min Range: -9.1473
Max Act: 8.2098. Min Act: -0.1700
Data Index: 5519647 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19