Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.8367. Min Act: -0.1700
Data Index: 1482584 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.8367. Min Act: -0.1700
Data Index: 7200281 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.8054. Min Act: -0.1700
Data Index: 1579075 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.7742. Min Act: -0.1700
Data Index: 4696924 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.7742. Min Act: -0.1700
Data Index: 610044 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.7742. Min Act: -0.1700
Data Index: 1642676 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.7429. Min Act: -0.1700
Data Index: 1770980 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.7117. Min Act: -0.1700
Data Index: 7861304 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.7117. Min Act: -0.1700
Data Index: 3597301 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6804. Min Act: -0.1700
Data Index: 2234555 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6804. Min Act: -0.1700
Data Index: 234678 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6804. Min Act: -0.1700
Data Index: 595957 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6804. Min Act: -0.1700
Data Index: 6667014 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6492. Min Act: -0.1700
Data Index: 106192 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6492. Min Act: -0.1700
Data Index: 2742372 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6804. Min Act: -0.1700
Data Index: 3261285 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6492. Min Act: -0.1700
Data Index: 8248253 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6492. Min Act: -0.1700
Data Index: 4311907 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6492. Min Act: -0.1700
Data Index: 314234 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8367. Min Range: -5.8367
Max Act: 5.6492. Min Act: -0.1700
Data Index: 2129942 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19