Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0709. Min Range: -3.0709
Max Act: 3.0709. Min Act: -0.1700
Data Index: 1135818 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0709. Min Range: -3.0709
Max Act: 3.0393. Min Act: -0.1700
Data Index: 7330453 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9286. Min Act: -0.1700
Data Index: 6402937 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9128. Min Act: -0.1700
Data Index: 5633951 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.9128. Min Act: -0.1700
Data Index: 4991230 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8652. Min Act: -0.1700
Data Index: 5129531 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8969. Min Act: -0.1700
Data Index: 5671298 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8652. Min Act: -0.1700
Data Index: 5981817 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8652. Min Act: -0.1700
Data Index: 3723521 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8493. Min Act: -0.1700
Data Index: 2502673 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8652. Min Act: -0.1700
Data Index: 5633942 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8493. Min Act: -0.1700
Data Index: 5256860 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8334. Min Act: -0.1700
Data Index: 379785 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8175. Min Act: -0.1700
Data Index: 6820232 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8175. Min Act: -0.1700
Data Index: 4666480 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8175. Min Act: -0.1700
Data Index: 5569547 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.8016. Min Act: -0.1700
Data Index: 4417231 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.7697. Min Act: -0.1700
Data Index: 5671297 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.7697. Min Act: -0.1700
Data Index: 4323804 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0709. Min Range: -3.0709
Max Act: 2.7378. Min Act: -0.1700
Data Index: 6893081 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19