Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2397. Min Range: -9.2397
Max Act: 9.2397. Min Act: -0.1700
Data Index: 1033796 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2397. Min Range: -9.2397
Max Act: 9.1772. Min Act: -0.1700
Data Index: 7255522 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.8022. Min Act: -0.1700
Data Index: 4701340 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.7397. Min Act: -0.1700
Data Index: 7205207 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.6147. Min Act: -0.1700
Data Index: 970127 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.6147. Min Act: -0.1700
Data Index: 2669180 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.5522. Min Act: -0.1700
Data Index: 183208 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.5522. Min Act: -0.1700
Data Index: 1914261 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.5522. Min Act: -0.1700
Data Index: 5132820 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4897. Min Act: -0.1700
Data Index: 5165510 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4897. Min Act: -0.1700
Data Index: 6979379 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4897. Min Act: -0.1700
Data Index: 4679266 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4272. Min Act: -0.1700
Data Index: 7602907 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4272. Min Act: -0.1700
Data Index: 558918 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4272. Min Act: -0.1700
Data Index: 6810652 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4272. Min Act: -0.1700
Data Index: 2745090 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.4272. Min Act: -0.1700
Data Index: 162139 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.3647. Min Act: -0.1700
Data Index: 5257274 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.3647. Min Act: -0.1700
Data Index: 1408494 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2397. Min Range: -9.2397
Max Act: 8.3647. Min Act: -0.1700
Data Index: 914332 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19