Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5894 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.2880. Min Act: -0.1700
Data Index: 1078322 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.2567. Min Act: -0.1700
Data Index: 4826970 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7489889 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1942. Min Act: -0.1700
Data Index: 5583846 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1630. Min Act: -0.1700
Data Index: 2523645 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1630. Min Act: -0.1700
Data Index: 612121 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1005. Min Act: -0.1700
Data Index: 2311025 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1317. Min Act: -0.1700
Data Index: 4999700 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1005. Min Act: -0.1700
Data Index: 4405608 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.1005. Min Act: -0.1700
Data Index: 3346937 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0692. Min Act: -0.1700
Data Index: 2165750 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0692. Min Act: -0.1700
Data Index: 2078034 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0380. Min Act: -0.1700
Data Index: 546509 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0380. Min Act: -0.1700
Data Index: 6737479 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0380. Min Act: -0.1700
Data Index: 4433122 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0067. Min Act: -0.1700
Data Index: 28714 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0380. Min Act: -0.1700
Data Index: 51404 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2880. Min Range: -5.2880
Max Act: 5.0067. Min Act: -0.1700
Data Index: 6497378 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2880. Min Range: -5.2880
Max Act: 4.9755. Min Act: -0.1700
Data Index: 1162457 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2880. Min Range: -5.2880
Max Act: 4.9755. Min Act: -0.1700
Data Index: 6486673 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19