Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.4631. Min Act: -0.1700
Data Index: 3333931 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.3381. Min Act: -0.1700
Data Index: 8565722 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2756. Min Act: -0.1700
Data Index: 1906685 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1818. Min Act: -0.1700
Data Index: 3665960 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0568. Min Act: -0.1700
Data Index: 7844237 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0568. Min Act: -0.1700
Data Index: 1262540 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0256. Min Act: -0.1700
Data Index: 3949122 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0256. Min Act: -0.1700
Data Index: 4092016 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.0568. Min Act: -0.1700
Data Index: 6298830 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 3435692 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 5312491 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 5173761 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 1019319 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 7696488 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 1296236 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9943. Min Act: -0.1700
Data Index: 8014523 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 4426893 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9631. Min Act: -0.1700
Data Index: 4014520 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.9318. Min Act: -0.1700
Data Index: 8031839 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4631. Min Range: -6.4631
Max Act: 5.8693. Min Act: -0.1700
Data Index: 3765272 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19