Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.7344. Min Act: -0.1700
Data Index: 7364959 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.5469. Min Act: -0.1700
Data Index: 8362941 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.4531. Min Act: -0.1700
Data Index: 6919853 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3790510 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.3906. Min Act: -0.1700
Data Index: 8475077 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.3906. Min Act: -0.1700
Data Index: 5268615 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.3594. Min Act: -0.1700
Data Index: 8766300 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.3281. Min Act: -0.1700
Data Index: 6180710 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.2969. Min Act: -0.1700
Data Index: 7863986 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.2344. Min Act: -0.1700
Data Index: 211817 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.2656. Min Act: -0.1700
Data Index: 7175646 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.2344. Min Act: -0.1700
Data Index: 7975623 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.2344. Min Act: -0.1700
Data Index: 242824 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.1719. Min Act: -0.1700
Data Index: 4589179 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.1719. Min Act: -0.1700
Data Index: 8433043 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.1719. Min Act: -0.1700
Data Index: 3161794 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.2031. Min Act: -0.1700
Data Index: 4750297 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.1406. Min Act: -0.1700
Data Index: 2478989 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.1094. Min Act: -0.1700
Data Index: 6445626 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7344. Min Range: -6.7344
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1789762 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19