Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 125 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.6974. Min Act: -0.1700
Data Index: 6473431 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.6349. Min Act: -0.1700
Data Index: 6502127 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.5724. Min Act: -0.1700
Data Index: 2722391 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.4474. Min Act: -0.1700
Data Index: 5856733 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.4474. Min Act: -0.1700
Data Index: 8281356 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.3849. Min Act: -0.1700
Data Index: 4604474 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.3224. Min Act: -0.1700
Data Index: 5424068 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.2599. Min Act: -0.1700
Data Index: 8024030 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.1974. Min Act: -0.1700
Data Index: 6836902 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.1349. Min Act: -0.1700
Data Index: 5017054 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.1349. Min Act: -0.1700
Data Index: 3199417 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.0724. Min Act: -0.1700
Data Index: 6318045 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.0724. Min Act: -0.1700
Data Index: 4023903 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.0099. Min Act: -0.1700
Data Index: 2765034 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.0099. Min Act: -0.1700
Data Index: 584202 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.0099. Min Act: -0.1700
Data Index: 3689367 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6974. Min Range: -8.6974
Max Act: 7.8849. Min Act: -0.1700
Data Index: 4907976 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6974. Min Range: -8.6974
Max Act: 7.9474. Min Act: -0.1700
Data Index: 7583289 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6974. Min Range: -8.6974
Max Act: 8.0099. Min Act: -0.1700
Data Index: 7203090 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6974. Min Range: -8.6974
Max Act: 7.9474. Min Act: -0.1700
Data Index: 5085817 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19