Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 577 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2001. Min Range: -8.2001
Max Act: 8.2001. Min Act: -0.1700
Data Index: 6349664 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.9501. Min Act: -0.1700
Data Index: 8762005 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.8876. Min Act: -0.1700
Data Index: 5291332 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.8876. Min Act: -0.1700
Data Index: 782291 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.8251. Min Act: -0.1700
Data Index: 741165 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.7313. Min Act: -0.1700
Data Index: 4402244 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.7626. Min Act: -0.1700
Data Index: 2191079 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.7001. Min Act: -0.1700
Data Index: 5348521 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.6688. Min Act: -0.1700
Data Index: 2854064 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.6063. Min Act: -0.1700
Data Index: 2904846 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.5751. Min Act: -0.1700
Data Index: 5332394 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.6063. Min Act: -0.1700
Data Index: 3246026 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.5751. Min Act: -0.1700
Data Index: 3591639 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.5751. Min Act: -0.1700
Data Index: 7885568 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.5126. Min Act: -0.1700
Data Index: 7528538 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.4813. Min Act: -0.1700
Data Index: 3908902 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.4813. Min Act: -0.1700
Data Index: 5650216 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.4501. Min Act: -0.1700
Data Index: 5849883 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.3876. Min Act: -0.1700
Data Index: 8527574 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2001. Min Range: -8.2001
Max Act: 7.4188. Min Act: -0.1700
Data Index: 4372181 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19