Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.7123. Min Act: -0.1700
Data Index: 1630525 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.6498. Min Act: -0.1700
Data Index: 4351499 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.5561. Min Act: -0.1700
Data Index: 8512654 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.4623. Min Act: -0.1700
Data Index: 8384875 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.4936. Min Act: -0.1700
Data Index: 6791731 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.4623. Min Act: -0.1700
Data Index: 3661146 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.4623. Min Act: -0.1700
Data Index: 6539254 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3998. Min Act: -0.1700
Data Index: 6068856 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3998. Min Act: -0.1700
Data Index: 8747388 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3686. Min Act: -0.1700
Data Index: 504900 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3686. Min Act: -0.1700
Data Index: 1406878 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3686. Min Act: -0.1700
Data Index: 6699239 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3061. Min Act: -0.1700
Data Index: 6907517 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.3061. Min Act: -0.1700
Data Index: 1889014 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.2748. Min Act: -0.1700
Data Index: 4677036 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.2748. Min Act: -0.1700
Data Index: 8489563 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.2748. Min Act: -0.1700
Data Index: 8413328 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.2435. Min Act: -0.1700
Data Index: 973000 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.2435. Min Act: -0.1700
Data Index: 4931776 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7123. Min Range: -4.7123
Max Act: 4.2435. Min Act: -0.1700
Data Index: 4714129 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19