Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.7824. Min Act: -0.1700
Data Index: 6422311 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.5949. Min Act: -0.1700
Data Index: 7782335 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.5636. Min Act: -0.1700
Data Index: 3920906 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.5324. Min Act: -0.1700
Data Index: 8815796 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.5011. Min Act: -0.1700
Data Index: 1661805 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.5011. Min Act: -0.1700
Data Index: 3348412 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.5324. Min Act: -0.1700
Data Index: 8681333 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4699. Min Act: -0.1700
Data Index: 7992267 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4699. Min Act: -0.1700
Data Index: 6724484 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4699. Min Act: -0.1700
Data Index: 10728 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4699. Min Act: -0.1700
Data Index: 4409352 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4386. Min Act: -0.1700
Data Index: 4576090 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4386. Min Act: -0.1700
Data Index: 4993778 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4074. Min Act: -0.1700
Data Index: 8195678 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.4386. Min Act: -0.1700
Data Index: 8013553 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.3761. Min Act: -0.1700
Data Index: 4574008 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.3761. Min Act: -0.1700
Data Index: 1427433 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.3136. Min Act: -0.1700
Data Index: 216757 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.2824. Min Act: -0.1700
Data Index: 1293430 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7824. Min Range: -6.7824
Max Act: 6.2824. Min Act: -0.1700
Data Index: 6710510 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19