Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1094 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.6559. Min Act: -0.1700
Data Index: 88183 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4997. Min Act: -0.1700
Data Index: 8047241 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4684. Min Act: -0.1700
Data Index: 1225162 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4684. Min Act: -0.1700
Data Index: 8576825 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4372. Min Act: -0.1700
Data Index: 8373185 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4372. Min Act: -0.1700
Data Index: 1360008 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4059. Min Act: -0.1700
Data Index: 1331902 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4059. Min Act: -0.1700
Data Index: 7421922 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4372. Min Act: -0.1700
Data Index: 172537 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.4059. Min Act: -0.1700
Data Index: 5364950 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3747. Min Act: -0.1700
Data Index: 7562224 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3747. Min Act: -0.1700
Data Index: 4404747 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3122. Min Act: -0.1700
Data Index: 5930144 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 8194202 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 1833426 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 5966805 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 6700473 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 4202937 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 4853560 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6559. Min Range: -4.6559
Max Act: 4.3434. Min Act: -0.1700
Data Index: 6267494 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19