Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.7912. Min Act: -0.1700
Data Index: 8426292 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.6349. Min Act: -0.1700
Data Index: 6351946 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.5724. Min Act: -0.1700
Data Index: 2149844 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.5099. Min Act: -0.1700
Data Index: 92406 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4787. Min Act: -0.1700
Data Index: 2889700 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 6954280 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 1734837 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.5099. Min Act: -0.1700
Data Index: 39538 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 3075643 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 7226294 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 3080164 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 7072942 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 5301341 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 107677 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 2114412 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 1171314 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4474. Min Act: -0.1700
Data Index: 6918358 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4162. Min Act: -0.1700
Data Index: 3083155 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4162. Min Act: -0.1700
Data Index: 1392446 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7912. Min Range: -5.7912
Max Act: 5.4162. Min Act: -0.1700
Data Index: 3230503 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19