Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1472 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.5186. Min Act: -0.1700
Data Index: 8135375 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.4248. Min Act: -0.1700
Data Index: 4064660 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.3623. Min Act: -0.1700
Data Index: 6301368 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2061. Min Act: -0.1700
Data Index: 414803 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.2061. Min Act: -0.1700
Data Index: 3098499 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1748. Min Act: -0.1700
Data Index: 209335 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1748. Min Act: -0.1700
Data Index: 2732324 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1123. Min Act: -0.1700
Data Index: 3814601 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1748. Min Act: -0.1700
Data Index: 2216754 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1123. Min Act: -0.1700
Data Index: 8180267 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1436. Min Act: -0.1700
Data Index: 3354036 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1123. Min Act: -0.1700
Data Index: 1091216 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1123. Min Act: -0.1700
Data Index: 3410337 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.1123. Min Act: -0.1700
Data Index: 1431112 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.0811. Min Act: -0.1700
Data Index: 714999 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.0811. Min Act: -0.1700
Data Index: 1566659 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.0811. Min Act: -0.1700
Data Index: 2753092 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.0498. Min Act: -0.1700
Data Index: 3634101 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.0811. Min Act: -0.1700
Data Index: 6380636 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5186. Min Range: -7.5186
Max Act: 7.0811. Min Act: -0.1700
Data Index: 6844096 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19