Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4817 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.5656. Min Act: -0.1700
Data Index: 8698253 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.5969. Min Act: -0.1700
Data Index: 6780651 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.5656. Min Act: -0.1700
Data Index: 4334563 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.5031. Min Act: -0.1700
Data Index: 4091512 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.4406. Min Act: -0.1700
Data Index: 1798747 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.4406. Min Act: -0.1700
Data Index: 211640 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3781. Min Act: -0.1700
Data Index: 3027915 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3469. Min Act: -0.1700
Data Index: 8395720 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3781. Min Act: -0.1700
Data Index: 8743967 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3469. Min Act: -0.1700
Data Index: 5310995 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3469. Min Act: -0.1700
Data Index: 2072385 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3469. Min Act: -0.1700
Data Index: 4993111 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3156. Min Act: -0.1700
Data Index: 7855927 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3469. Min Act: -0.1700
Data Index: 4091511 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3156. Min Act: -0.1700
Data Index: 42140 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3156. Min Act: -0.1700
Data Index: 605306 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.3156. Min Act: -0.1700
Data Index: 734554 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.2844. Min Act: -0.1700
Data Index: 1437966 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.2844. Min Act: -0.1700
Data Index: 8168043 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5969. Min Range: -4.5969
Max Act: 4.2844. Min Act: -0.1700
Data Index: 2396583 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19