Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.7501. Min Act: -0.1700
Data Index: 2739169 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.7501. Min Act: -0.1700
Data Index: 7851260 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.6251. Min Act: -0.1700
Data Index: 3170872 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5626. Min Act: -0.1700
Data Index: 1602648 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5313. Min Act: -0.1700
Data Index: 2618868 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5313. Min Act: -0.1700
Data Index: 8228558 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5001. Min Act: -0.1700
Data Index: 3008698 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5001. Min Act: -0.1700
Data Index: 636164 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5001. Min Act: -0.1700
Data Index: 1228290 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5001. Min Act: -0.1700
Data Index: 3483211 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5001. Min Act: -0.1700
Data Index: 8392079 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4376. Min Act: -0.1700
Data Index: 1775692 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.5001. Min Act: -0.1700
Data Index: 6848384 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4688. Min Act: -0.1700
Data Index: 7544061 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4376. Min Act: -0.1700
Data Index: 8453917 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4556021 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4376. Min Act: -0.1700
Data Index: 8763258 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4376. Min Act: -0.1700
Data Index: 6628807 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4376. Min Act: -0.1700
Data Index: 8410724 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7501. Min Range: -5.7501
Max Act: 5.4063. Min Act: -0.1700
Data Index: 1003187 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19