Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 442 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.5099. Min Act: -0.1700
Data Index: 8500541 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4835. Min Act: -0.1700
Data Index: 2516260 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4835. Min Act: -0.1700
Data Index: 2412260 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4572. Min Act: -0.1700
Data Index: 2566669 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4484. Min Act: -0.1700
Data Index: 8532027 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4396. Min Act: -0.1700
Data Index: 1980288 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4220. Min Act: -0.1700
Data Index: 2352483 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4396. Min Act: -0.1700
Data Index: 8664356 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4220. Min Act: -0.1700
Data Index: 5889397 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4132. Min Act: -0.1700
Data Index: 3469633 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4220. Min Act: -0.1700
Data Index: 6579255 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4132. Min Act: -0.1700
Data Index: 3328627 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4044. Min Act: -0.1700
Data Index: 7717583 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4044. Min Act: -0.1700
Data Index: 6940917 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4132. Min Act: -0.1700
Data Index: 2636832 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4044. Min Act: -0.1700
Data Index: 205493 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4132. Min Act: -0.1700
Data Index: 6662536 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4044. Min Act: -0.1700
Data Index: 2605510 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4044. Min Act: -0.1700
Data Index: 3690028 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5099. Min Range: -1.5099
Max Act: 1.4132. Min Act: -0.1700
Data Index: 4683771 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19