Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1325. Min Range: -6.1325
Max Act: 6.1325. Min Act: -0.1700
Data Index: 90761 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.9762. Min Act: -0.1700
Data Index: 2161915 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.9450. Min Act: -0.1700
Data Index: 264319 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.9450. Min Act: -0.1700
Data Index: 5987878 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.8825. Min Act: -0.1700
Data Index: 6639471 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.8512. Min Act: -0.1700
Data Index: 7865430 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.8825. Min Act: -0.1700
Data Index: 6129676 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.7887. Min Act: -0.1700
Data Index: 3690382 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.7887. Min Act: -0.1700
Data Index: 6228315 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.7262. Min Act: -0.1700
Data Index: 6313435 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6637. Min Act: -0.1700
Data Index: 7406485 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6637. Min Act: -0.1700
Data Index: 6228314 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6637. Min Act: -0.1700
Data Index: 6285564 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6325. Min Act: -0.1700
Data Index: 3296422 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6325. Min Act: -0.1700
Data Index: 5647120 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.5700. Min Act: -0.1700
Data Index: 5982328 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6012. Min Act: -0.1700
Data Index: 946583 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.5700. Min Act: -0.1700
Data Index: 7105063 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.6012. Min Act: -0.1700
Data Index: 7300738 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1325. Min Range: -6.1325
Max Act: 5.5700. Min Act: -0.1700
Data Index: 4568238 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19