Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2326. Min Range: -8.2326
Max Act: 8.2326. Min Act: -0.1700
Data Index: 3956165 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.9201. Min Act: -0.1700
Data Index: 792334 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.8576. Min Act: -0.1700
Data Index: 1948673 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.7639. Min Act: -0.1700
Data Index: 8519980 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.6701. Min Act: -0.1700
Data Index: 1651819 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.6389. Min Act: -0.1700
Data Index: 8445384 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.6389. Min Act: -0.1700
Data Index: 2538629 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.6076. Min Act: -0.1700
Data Index: 3105800 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.6076. Min Act: -0.1700
Data Index: 6423061 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.5451. Min Act: -0.1700
Data Index: 6435622 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.5451. Min Act: -0.1700
Data Index: 3637726 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.5451. Min Act: -0.1700
Data Index: 210560 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.4826. Min Act: -0.1700
Data Index: 4987280 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.5139. Min Act: -0.1700
Data Index: 1078621 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.5139. Min Act: -0.1700
Data Index: 1912046 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.4826. Min Act: -0.1700
Data Index: 3015581 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.4826. Min Act: -0.1700
Data Index: 4144316 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.4826. Min Act: -0.1700
Data Index: 2637906 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.5139. Min Act: -0.1700
Data Index: 4180733 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2326. Min Range: -8.2326
Max Act: 7.4514. Min Act: -0.1700
Data Index: 5173246 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19