Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.5036. Min Act: -0.1700
Data Index: 1635639 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.3161. Min Act: -0.1700
Data Index: 1343375 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.2848. Min Act: -0.1700
Data Index: 5053406 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.2848. Min Act: -0.1700
Data Index: 464312 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.2536. Min Act: -0.1700
Data Index: 464310 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1911. Min Act: -0.1700
Data Index: 464309 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1911. Min Act: -0.1700
Data Index: 464320 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1911. Min Act: -0.1700
Data Index: 6226758 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1598. Min Act: -0.1700
Data Index: 464316 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1598. Min Act: -0.1700
Data Index: 464313 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1598. Min Act: -0.1700
Data Index: 8070792 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1286. Min Act: -0.1700
Data Index: 7869892 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.1286. Min Act: -0.1700
Data Index: 5710738 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0973. Min Act: -0.1700
Data Index: 500790 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0973. Min Act: -0.1700
Data Index: 5187384 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0661. Min Act: -0.1700
Data Index: 1010506 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0348. Min Act: -0.1700
Data Index: 5053407 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0661. Min Act: -0.1700
Data Index: 861626 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0348. Min Act: -0.1700
Data Index: 8693173 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5036. Min Range: -6.5036
Max Act: 6.0036. Min Act: -0.1700
Data Index: 908993 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19