Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.3520. Min Act: -0.1700
Data Index: 1780084 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.2270. Min Act: -0.1700
Data Index: 5338093 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1957. Min Act: -0.1700
Data Index: 5586807 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1645. Min Act: -0.1700
Data Index: 6166911 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1645. Min Act: -0.1700
Data Index: 6931333 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1957. Min Act: -0.1700
Data Index: 8254405 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1645. Min Act: -0.1700
Data Index: 2337355 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1332. Min Act: -0.1699
Data Index: 7227725 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1332. Min Act: -0.1700
Data Index: 2673669 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1332. Min Act: -0.1700
Data Index: 7383576 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1332. Min Act: -0.1700
Data Index: 2385462 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1332. Min Act: -0.1700
Data Index: 1342656 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1332. Min Act: -0.1700
Data Index: 5170810 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 3493170 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 456598 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 3742079 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 7082051 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 8491597 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 1673470 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3520. Min Range: -6.3520
Max Act: 6.1020. Min Act: -0.1700
Data Index: 4575829 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19