Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9938. Min Act: -0.1700
Data Index: 8739486 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9769. Min Act: -0.1700
Data Index: 1071025 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9854. Min Act: -0.1700
Data Index: 562855 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9515. Min Act: -0.1700
Data Index: 7212685 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9600. Min Act: -0.1700
Data Index: 4322729 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9600. Min Act: -0.1700
Data Index: 6042459 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9515. Min Act: -0.1700
Data Index: 2717020 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9515. Min Act: -0.1700
Data Index: 1208006 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9430. Min Act: -0.1700
Data Index: 7098858 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9515. Min Act: -0.1699
Data Index: 1879767 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9430. Min Act: -0.1700
Data Index: 2717019 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9260. Min Act: -0.1698
Data Index: 2620865 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9345. Min Act: -0.1700
Data Index: 7159589 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9260. Min Act: -0.1699
Data Index: 2717021 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9345. Min Act: -0.1700
Data Index: 5804437 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9260. Min Act: -0.1699
Data Index: 5542675 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9090. Min Act: -0.1700
Data Index: 3123163 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9175. Min Act: -0.1700
Data Index: 951783 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9090. Min Act: -0.1700
Data Index: 1055397 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9938. Min Range: -1.9938
Max Act: 1.9090. Min Act: -0.1700
Data Index: 1827795 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19