Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.8216. Min Act: -0.1700
Data Index: 3951738 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.7591. Min Act: -0.1700
Data Index: 6903639 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.6341. Min Act: -0.1700
Data Index: 6903618 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.5716. Min Act: -0.1700
Data Index: 6903633 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.4779. Min Act: -0.1700
Data Index: 6903613 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.4466. Min Act: -0.1700
Data Index: 4246322 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.4154. Min Act: -0.1700
Data Index: 2884898 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.3841. Min Act: -0.1700
Data Index: 2884903 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.3216. Min Act: -0.1700
Data Index: 5973123 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.3529. Min Act: -0.1700
Data Index: 7185010 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.2904. Min Act: -0.1700
Data Index: 3080159 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.2904. Min Act: -0.1700
Data Index: 8738239 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.2279. Min Act: -0.1700
Data Index: 331049 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1966. Min Act: -0.1700
Data Index: 6057561 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1966. Min Act: -0.1700
Data Index: 1382157 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1654. Min Act: -0.1700
Data Index: 4224462 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1341. Min Act: -0.1700
Data Index: 8301413 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1029. Min Act: -0.1700
Data Index: 5446249 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1029. Min Act: -0.1700
Data Index: 1474493 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8216. Min Range: -6.8216
Max Act: 6.1029. Min Act: -0.1700
Data Index: 2438123 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19