Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5018 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5009. Min Range: -10.5009
Max Act: 10.5009. Min Act: -0.1700
Data Index: 5020534 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5009. Min Range: -10.5009
Max Act: 10.1884. Min Act: -0.1700
Data Index: 6998586 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5009. Min Range: -10.5009
Max Act: 10.1259. Min Act: -0.1700
Data Index: 5840107 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.7509. Min Act: -0.1700
Data Index: 2418996 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.7509. Min Act: -0.1700
Data Index: 543395 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.7509. Min Act: -0.1700
Data Index: 409316 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.6259. Min Act: -0.1700
Data Index: 2250272 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.6884. Min Act: -0.1700
Data Index: 7590899 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.6884. Min Act: -0.1700
Data Index: 2250275 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.6259. Min Act: -0.1700
Data Index: 6875037 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5634. Min Act: -0.1700
Data Index: 4361021 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5634. Min Act: -0.1700
Data Index: 8545285 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5634. Min Act: -0.1700
Data Index: 5543523 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5009. Min Act: -0.1700
Data Index: 1692057 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5009. Min Act: -0.1700
Data Index: 3294621 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5634. Min Act: -0.1700
Data Index: 7200216 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.5009. Min Act: -0.1700
Data Index: 6566262 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.4384. Min Act: -0.1700
Data Index: 4612754 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.4384. Min Act: -0.1700
Data Index: 1353853 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5009. Min Range: -10.5009
Max Act: 9.4384. Min Act: -0.1700
Data Index: 232486 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19