Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3270 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0879. Min Range: -4.0879
Max Act: 4.0879. Min Act: -0.1700
Data Index: 3290357 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0879. Min Range: -4.0879
Max Act: 4.0879. Min Act: -0.1700
Data Index: 7501565 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0879. Min Range: -4.0879
Max Act: 4.0254. Min Act: -0.1700
Data Index: 6198705 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.9003. Min Act: -0.1700
Data Index: 4419381 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.8378. Min Act: -0.1700
Data Index: 3314101 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.8378. Min Act: -0.1700
Data Index: 8327707 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.8065. Min Act: -0.1700
Data Index: 1631496 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.7752. Min Act: -0.1700
Data Index: 1337314 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.7439. Min Act: -0.1700
Data Index: 5831494 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.7283. Min Act: -0.1700
Data Index: 7885741 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.7283. Min Act: -0.1700
Data Index: 4985498 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.7127. Min Act: -0.1700
Data Index: 7533661 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.6970. Min Act: -0.1700
Data Index: 6251880 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.6814. Min Act: -0.1700
Data Index: 3154530 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.6031. Min Act: -0.1700
Data Index: 4966086 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.6188. Min Act: -0.1700
Data Index: 7566594 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.6031. Min Act: -0.1700
Data Index: 8268153 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.5718. Min Act: -0.1700
Data Index: 1944994 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.5875. Min Act: -0.1700
Data Index: 3209002 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0879. Min Range: -4.0879
Max Act: 3.5718. Min Act: -0.1700
Data Index: 2563754 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19