Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.6496. Min Act: -0.1700
Data Index: 1103396 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.5246. Min Act: -0.1700
Data Index: 2728891 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.5246. Min Act: -0.1700
Data Index: 5167611 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.4933. Min Act: -0.1700
Data Index: 6264952 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.4621. Min Act: -0.1700
Data Index: 8243629 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.4308. Min Act: -0.1700
Data Index: 3128964 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.3996. Min Act: -0.1700
Data Index: 6727449 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.3996. Min Act: -0.1700
Data Index: 2612344 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.3996. Min Act: -0.1700
Data Index: 2511442 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.3683. Min Act: -0.1700
Data Index: 5528472 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.3371. Min Act: -0.1700
Data Index: 5123953 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2746. Min Act: -0.1700
Data Index: 921618 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2746. Min Act: -0.1700
Data Index: 3469849 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2746. Min Act: -0.1700
Data Index: 8090380 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2746. Min Act: -0.1700
Data Index: 305656 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2746. Min Act: -0.1700
Data Index: 2037062 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2433. Min Act: -0.1700
Data Index: 3822410 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2433. Min Act: -0.1700
Data Index: 1095105 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2121. Min Act: -0.1700
Data Index: 3453644 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6496. Min Range: -4.6496
Max Act: 4.2121. Min Act: -0.1700
Data Index: 2086232 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19