Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.5809. Min Act: -0.1700
Data Index: 8165586 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.2684. Min Act: -0.1700
Data Index: 8156985 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.3309. Min Act: -0.1700
Data Index: 1012216 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.1434. Min Act: -0.1700
Data Index: 3798337 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.2059. Min Act: -0.1700
Data Index: 1829999 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.2059. Min Act: -0.1700
Data Index: 8559011 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.1434. Min Act: -0.1700
Data Index: 2931685 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.1434. Min Act: -0.1700
Data Index: 5870194 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.1434. Min Act: -0.1700
Data Index: 3803446 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0809. Min Act: -0.1700
Data Index: 3554572 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0809. Min Act: -0.1700
Data Index: 5365596 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0184. Min Act: -0.1700
Data Index: 8447172 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0184. Min Act: -0.1700
Data Index: 5597068 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0184. Min Act: -0.1700
Data Index: 6018355 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0184. Min Act: -0.1700
Data Index: 2270679 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0809. Min Act: -0.1700
Data Index: 1085982 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5809. Min Range: -9.5809
Max Act: 9.0184. Min Act: -0.1700
Data Index: 4656339 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5809. Min Range: -9.5809
Max Act: 8.9559. Min Act: -0.1700
Data Index: 7374328 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5809. Min Range: -9.5809
Max Act: 8.9559. Min Act: -0.1700
Data Index: 3548531 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5809. Min Range: -9.5809
Max Act: 8.8934. Min Act: -0.1700
Data Index: 3728521 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19