Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2752 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.5537. Min Act: -0.1700
Data Index: 8194886 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.2724. Min Act: -0.1700
Data Index: 122864 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0849. Min Act: -0.1700
Data Index: 5184762 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.1162. Min Act: -0.1700
Data Index: 6569186 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.1162. Min Act: -0.1700
Data Index: 7105893 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.1162. Min Act: -0.1700
Data Index: 614367 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.1162. Min Act: -0.1700
Data Index: 8515188 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.1162. Min Act: -0.1700
Data Index: 1642730 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0849. Min Act: -0.1700
Data Index: 3384084 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0849. Min Act: -0.1700
Data Index: 3697189 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0537. Min Act: -0.1700
Data Index: 5082829 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0537. Min Act: -0.1700
Data Index: 8780891 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0224. Min Act: -0.1700
Data Index: 8742125 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0537. Min Act: -0.1700
Data Index: 7526568 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0537. Min Act: -0.1700
Data Index: 670059 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0224. Min Act: -0.1700
Data Index: 966068 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5537. Min Range: -6.5537
Max Act: 5.9912. Min Act: -0.1700
Data Index: 2710740 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0224. Min Act: -0.1700
Data Index: 1408719 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0224. Min Act: -0.1700
Data Index: 4200525 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5537. Min Range: -6.5537
Max Act: 6.0537. Min Act: -0.1700
Data Index: 4392207 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19