Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.9448. Min Act: -0.1700
Data Index: 8546484 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.6010. Min Act: -0.1700
Data Index: 7765574 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5385. Min Act: -0.1700
Data Index: 4230274 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5073. Min Act: -0.1700
Data Index: 2900540 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 4661122 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 4082351 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 2867374 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 8534996 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 3911061 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 8657974 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.4135. Min Act: -0.1700
Data Index: 7765576 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3823. Min Act: -0.1700
Data Index: 2224743 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3823. Min Act: -0.1700
Data Index: 400686 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3823. Min Act: -0.1700
Data Index: 452715 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3823. Min Act: -0.1700
Data Index: 6466402 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3823. Min Act: -0.1700
Data Index: 3085862 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3510. Min Act: -0.1700
Data Index: 6478115 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3510. Min Act: -0.1700
Data Index: 5223333 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.2885. Min Act: -0.1700
Data Index: 252466 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.3510. Min Act: -0.1700
Data Index: 4392918 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19