Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.2927. Min Act: -0.1700
Data Index: 1173313 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.1365. Min Act: -0.1700
Data Index: 3076250 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.1365. Min Act: -0.1700
Data Index: 3450396 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0740. Min Act: -0.1700
Data Index: 4998570 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0427. Min Act: -0.1700
Data Index: 7594090 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0427. Min Act: -0.1700
Data Index: 2683763 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0115. Min Act: -0.1700
Data Index: 8770972 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0115. Min Act: -0.1700
Data Index: 5711034 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0115. Min Act: -0.1700
Data Index: 3862015 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0115. Min Act: -0.1700
Data Index: 2683764 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0115. Min Act: -0.1700
Data Index: 3911064 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2927. Min Range: -5.2927
Max Act: 5.0115. Min Act: -0.1700
Data Index: 5711038 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9802. Min Act: -0.1700
Data Index: 4207486 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9802. Min Act: -0.1700
Data Index: 2793563 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9802. Min Act: -0.1700
Data Index: 5711031 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9490. Min Act: -0.1700
Data Index: 3003665 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9490. Min Act: -0.1700
Data Index: 4455496 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9802. Min Act: -0.1700
Data Index: 3911062 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9490. Min Act: -0.1700
Data Index: 50351 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2927. Min Range: -5.2927
Max Act: 4.9490. Min Act: -0.1700
Data Index: 4699348 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19