Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2470 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.9708. Min Act: -0.1700
Data Index: 1877384 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.8146. Min Act: -0.1700
Data Index: 5248435 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.6583. Min Act: -0.1700
Data Index: 2711324 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.5646. Min Act: -0.1700
Data Index: 7614052 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.5021. Min Act: -0.1700
Data Index: 1225752 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.3458. Min Act: -0.1700
Data Index: 31976 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.2833. Min Act: -0.1700
Data Index: 2062145 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.2521. Min Act: -0.1700
Data Index: 5612945 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.2521. Min Act: -0.1700
Data Index: 7366882 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.2208. Min Act: -0.1700
Data Index: 3030403 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1896. Min Act: -0.1700
Data Index: 3739556 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1583. Min Act: -0.1700
Data Index: 5569776 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1583. Min Act: -0.1700
Data Index: 134822 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1271. Min Act: -0.1700
Data Index: 3061575 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1271. Min Act: -0.1700
Data Index: 8363358 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1271. Min Act: -0.1700
Data Index: 3576641 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.0958. Min Act: -0.1700
Data Index: 6453292 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.0333. Min Act: -0.1700
Data Index: 5994004 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.1271. Min Act: -0.1700
Data Index: 6503463 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9708. Min Range: -5.9708
Max Act: 5.0958. Min Act: -0.1700
Data Index: 739489 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19