Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.5204. Min Act: -0.1700
Data Index: 4784394 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.4267. Min Act: -0.1700
Data Index: 8584664 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.4267. Min Act: -0.1700
Data Index: 7083929 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.3954. Min Act: -0.1700
Data Index: 1727080 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.3642. Min Act: -0.1700
Data Index: 6738693 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.2392. Min Act: -0.1700
Data Index: 2938432 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.2392. Min Act: -0.1700
Data Index: 1839718 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.2079. Min Act: -0.1700
Data Index: 4431707 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.1767. Min Act: -0.1700
Data Index: 3236786 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.1454. Min Act: -0.1700
Data Index: 2577955 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.1454. Min Act: -0.1700
Data Index: 1065239 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.1454. Min Act: -0.1700
Data Index: 871919 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0829. Min Act: -0.1700
Data Index: 3898429 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0829. Min Act: -0.1700
Data Index: 6742621 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0517. Min Act: -0.1700
Data Index: 3931179 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0517. Min Act: -0.1700
Data Index: 723924 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0517. Min Act: -0.1700
Data Index: 1393007 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0517. Min Act: -0.1700
Data Index: 1448869 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0204. Min Act: -0.1700
Data Index: 6352561 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5204. Min Range: -6.5204
Max Act: 6.0204. Min Act: -0.1700
Data Index: 7741967 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19