Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6334. Min Range: -12.6334
Max Act: 12.6334. Min Act: -0.1700
Data Index: 7640747 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6334. Min Range: -12.6334
Max Act: 12.0709. Min Act: -0.1700
Data Index: 5476332 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6334. Min Range: -12.6334
Max Act: 12.0709. Min Act: -0.1700
Data Index: 4722341 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6334. Min Range: -12.6334
Max Act: 12.0709. Min Act: -0.1700
Data Index: 8198586 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6334. Min Range: -12.6334
Max Act: 12.0709. Min Act: -0.1700
Data Index: 264691 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.9459. Min Act: -0.1700
Data Index: 1852296 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.9459. Min Act: -0.1700
Data Index: 1887139 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.9459. Min Act: -0.1700
Data Index: 5724919 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.8834. Min Act: -0.1700
Data Index: 4275546 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.8209. Min Act: -0.1700
Data Index: 3146627 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.8209. Min Act: -0.1700
Data Index: 866833 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.8209. Min Act: -0.1700
Data Index: 4521704 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.8834. Min Act: -0.1700
Data Index: 1054054 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.6959. Min Act: -0.1700
Data Index: 1970363 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.7584. Min Act: -0.1700
Data Index: 6055534 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.7584. Min Act: -0.1700
Data Index: 3971901 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.7584. Min Act: -0.1700
Data Index: 8690973 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.7584. Min Act: -0.1700
Data Index: 8525684 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.6959. Min Act: -0.1700
Data Index: 3807833 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6334. Min Range: -12.6334
Max Act: 11.6959. Min Act: -0.1700
Data Index: 847731 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19