Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4816 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0189. Min Range: -9.0189
Max Act: 9.0189. Min Act: -0.1699
Data Index: 6616347 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0189. Min Range: -9.0189
Max Act: 9.0189. Min Act: -0.1700
Data Index: 3813784 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.8939. Min Act: -0.1700
Data Index: 3813779 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.9564. Min Act: -0.1700
Data Index: 6616351 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.8314. Min Act: -0.1700
Data Index: 3239351 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.7689. Min Act: -0.1700
Data Index: 6186874 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.7689. Min Act: -0.1700
Data Index: 4918683 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.7064. Min Act: -0.1700
Data Index: 8036029 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.6439. Min Act: -0.1700
Data Index: 6028709 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 7216093 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5189. Min Act: -0.1700
Data Index: 880098 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 7463054 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 7463053 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.6439. Min Act: -0.1700
Data Index: 8482259 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.6439. Min Act: -0.1700
Data Index: 8138593 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 6737283 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 4186727 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 8036030 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5814. Min Act: -0.1700
Data Index: 1270891 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0189. Min Range: -9.0189
Max Act: 8.5189. Min Act: -0.1700
Data Index: 3325209 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19