Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.7326. Min Act: -0.1700
Data Index: 1476637 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.5451. Min Act: -0.1700
Data Index: 7891395 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.5451. Min Act: -0.1700
Data Index: 8082238 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.4826. Min Act: -0.1700
Data Index: 1342688 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.4826. Min Act: -0.1700
Data Index: 706694 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.4826. Min Act: -0.1700
Data Index: 3959669 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.4826. Min Act: -0.1700
Data Index: 5933551 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.3576. Min Act: -0.1700
Data Index: 1653466 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.3576. Min Act: -0.1700
Data Index: 5708889 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.3576. Min Act: -0.1700
Data Index: 3056837 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.3576. Min Act: -0.1700
Data Index: 6247706 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.2951. Min Act: -0.1700
Data Index: 2487532 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.3576. Min Act: -0.1700
Data Index: 7978881 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.2951. Min Act: -0.1700
Data Index: 2516222 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.2951. Min Act: -0.1700
Data Index: 123558 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.2951. Min Act: -0.1700
Data Index: 4705265 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.2951. Min Act: -0.1700
Data Index: 5526585 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.2326. Min Act: -0.1700
Data Index: 598026 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.1701. Min Act: -0.1700
Data Index: 3385578 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7326. Min Range: -8.7326
Max Act: 8.1701. Min Act: -0.1700
Data Index: 7606578 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19