Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.6559. Min Act: -0.1700
Data Index: 2305202 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2809. Min Act: -0.1700
Data Index: 1945701 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2809. Min Act: -0.1700
Data Index: 1082321 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2809. Min Act: -0.1700
Data Index: 2356815 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1871. Min Act: -0.1700
Data Index: 1498865 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1559. Min Act: -0.1700
Data Index: 3386042 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1246. Min Act: -0.1700
Data Index: 28646 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0934. Min Act: -0.1700
Data Index: 6919431 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0934. Min Act: -0.1700
Data Index: 121694 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0621. Min Act: -0.1700
Data Index: 5360987 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0621. Min Act: -0.1700
Data Index: 5762294 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0309. Min Act: -0.1700
Data Index: 7751592 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0309. Min Act: -0.1700
Data Index: 5333929 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9996. Min Act: -0.1700
Data Index: 5171108 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9684. Min Act: -0.1700
Data Index: 7528247 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9371. Min Act: -0.1700
Data Index: 4023667 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9996. Min Act: -0.1700
Data Index: 7730989 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9684. Min Act: -0.1700
Data Index: 3537321 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9684. Min Act: -0.1700
Data Index: 955737 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6559. Min Range: -6.6559
Max Act: 5.9684. Min Act: -0.1700
Data Index: 6370774 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19