Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2528. Min Range: -6.2528
Max Act: 6.2528. Min Act: -0.1700
Data Index: 4093795 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2528. Min Range: -6.2528
Max Act: 6.1591. Min Act: -0.1700
Data Index: 7735201 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2528. Min Range: -6.2528
Max Act: 6.0653. Min Act: -0.1700
Data Index: 7286603 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2528. Min Range: -6.2528
Max Act: 6.0341. Min Act: -0.1700
Data Index: 3722943 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.8778. Min Act: -0.1700
Data Index: 1229780 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.9091. Min Act: -0.1700
Data Index: 6614992 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.8153. Min Act: -0.1700
Data Index: 2407591 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.7216. Min Act: -0.1700
Data Index: 1224809 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.7528. Min Act: -0.1700
Data Index: 1689487 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.7841. Min Act: -0.1700
Data Index: 787383 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.7841. Min Act: -0.1700
Data Index: 5573335 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.6903. Min Act: -0.1700
Data Index: 2450133 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.7216. Min Act: -0.1700
Data Index: 5703041 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.6903. Min Act: -0.1700
Data Index: 6834935 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.6278. Min Act: -0.1700
Data Index: 3131173 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.6278. Min Act: -0.1700
Data Index: 5449723 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.5653. Min Act: -0.1700
Data Index: 3315824 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.5653. Min Act: -0.1700
Data Index: 3071948 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.5028. Min Act: -0.1700
Data Index: 6006284 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2528. Min Range: -6.2528
Max Act: 5.5028. Min Act: -0.1700
Data Index: 2253022 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19