Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.8301. Min Act: -0.1700
Data Index: 2429656 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.7676. Min Act: -0.1700
Data Index: 8678020 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.7363. Min Act: -0.1700
Data Index: 6409343 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 5964624 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 597413 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.7051. Min Act: -0.1700
Data Index: 1657428 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6738. Min Act: -0.1700
Data Index: 8757598 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6738. Min Act: -0.1700
Data Index: 4109502 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6738. Min Act: -0.1700
Data Index: 6199765 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6738. Min Act: -0.1700
Data Index: 5271730 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6113. Min Act: -0.1700
Data Index: 5601850 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6113. Min Act: -0.1700
Data Index: 7578175 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6113. Min Act: -0.1700
Data Index: 204186 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6113. Min Act: -0.1700
Data Index: 3852822 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6113. Min Act: -0.1700
Data Index: 5321847 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.5801. Min Act: -0.1700
Data Index: 1146772 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.6113. Min Act: -0.1700
Data Index: 2413180 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.5801. Min Act: -0.1700
Data Index: 1264461 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.5801. Min Act: -0.1700
Data Index: 4604450 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8301. Min Range: -4.8301
Max Act: 4.5801. Min Act: -0.1700
Data Index: 635168 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19