Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.7123. Min Act: -0.1700
Data Index: 6882544 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.6186. Min Act: -0.1700
Data Index: 3207759 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.5561. Min Act: -0.1700
Data Index: 8513045 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.5248. Min Act: -0.1700
Data Index: 7044460 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.4936. Min Act: -0.1700
Data Index: 8451273 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.4936. Min Act: -0.1700
Data Index: 6003694 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3067923 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.4623. Min Act: -0.1700
Data Index: 7395488 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.4311. Min Act: -0.1700
Data Index: 2726691 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3686. Min Act: -0.1700
Data Index: 1224412 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3686. Min Act: -0.1700
Data Index: 2641336 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3686. Min Act: -0.1700
Data Index: 5843911 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3686. Min Act: -0.1700
Data Index: 4958891 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 4354382 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 1565785 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 3495659 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 6427168 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 4928217 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 2701387 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7123. Min Range: -5.7123
Max Act: 5.3373. Min Act: -0.1700
Data Index: 2620162 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19