Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.4123. Min Act: -0.1700
Data Index: 2334394 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.3811. Min Act: -0.1700
Data Index: 2475886 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.2873. Min Act: -0.1700
Data Index: 1319043 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.2248. Min Act: -0.1700
Data Index: 4333343 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.1623. Min Act: -0.1700
Data Index: 8671960 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0998. Min Act: -0.1700
Data Index: 4738521 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0686. Min Act: -0.1700
Data Index: 2646323 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0686. Min Act: -0.1700
Data Index: 3373427 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0373. Min Act: -0.1700
Data Index: 2209191 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0373. Min Act: -0.1700
Data Index: 8466609 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0373. Min Act: -0.1700
Data Index: 2606328 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4123. Min Range: -5.4123
Max Act: 5.0373. Min Act: -0.1700
Data Index: 3474180 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9748. Min Act: -0.1700
Data Index: 6576331 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9748. Min Act: -0.1700
Data Index: 1866589 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9748. Min Act: -0.1700
Data Index: 5766219 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2559078 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2030796 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9436. Min Act: -0.1700
Data Index: 8182954 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2007051 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4123. Min Range: -5.4123
Max Act: 4.9436. Min Act: -0.1700
Data Index: 7010577 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19