Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.4375. Min Act: -0.1700
Data Index: 818295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.4375. Min Act: -0.1700
Data Index: 1473838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.4062. Min Act: -0.1700
Data Index: 467053 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3591. Min Act: -0.1700
Data Index: 8243182 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3591. Min Act: -0.1700
Data Index: 2496397 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3434. Min Act: -0.1700
Data Index: 8202769 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3434. Min Act: -0.1700
Data Index: 8268005 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3434. Min Act: -0.1700
Data Index: 8539299 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3434. Min Act: -0.1700
Data Index: 6483966 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 6884984 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 4348525 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 2200955 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 2090501 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3434. Min Act: -0.1700
Data Index: 8832464 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 813067 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 2606902 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3278. Min Act: -0.1700
Data Index: 514452 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.2964. Min Act: -0.1700
Data Index: 3253706 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3121. Min Act: -0.1700
Data Index: 310409 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4375. Min Range: -3.4375
Max Act: 3.3121. Min Act: -0.1700
Data Index: 3695466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19