Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6158552 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.2298. Min Act: -0.1700
Data Index: 1087795 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.0736. Min Act: -0.1700
Data Index: 5518242 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.0423. Min Act: -0.1700
Data Index: 3952657 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.0423. Min Act: -0.1700
Data Index: 970149 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.0111. Min Act: -0.1700
Data Index: 3357638 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.0111. Min Act: -0.1700
Data Index: 2450470 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.9798. Min Act: -0.1700
Data Index: 7259601 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.9798. Min Act: -0.1700
Data Index: 5162642 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.9486. Min Act: -0.1700
Data Index: 4153493 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.9486. Min Act: -0.1700
Data Index: 559862 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.9486. Min Act: -0.1700
Data Index: 8114756 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8861. Min Act: -0.1700
Data Index: 3527628 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8861. Min Act: -0.1700
Data Index: 5755457 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8548. Min Act: -0.1700
Data Index: 4510710 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8548. Min Act: -0.1700
Data Index: 2542795 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8548. Min Act: -0.1700
Data Index: 5939379 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8236. Min Act: -0.1700
Data Index: 1905837 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8236. Min Act: -0.1700
Data Index: 1231250 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.7923. Min Act: -0.1700
Data Index: 5141509 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19