Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1479. Min Range: -8.1479
Max Act: 8.1479. Min Act: -0.1700
Data Index: 3396266 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.9604. Min Act: -0.1700
Data Index: 1735758 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.6166. Min Act: -0.1700
Data Index: 3294493 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.6166. Min Act: -0.1700
Data Index: 1955979 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.5541. Min Act: -0.1700
Data Index: 2074567 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.3979. Min Act: -0.1700
Data Index: 5393033 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.3354. Min Act: -0.1700
Data Index: 7798233 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.3041. Min Act: -0.1700
Data Index: 2310165 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.2729. Min Act: -0.1700
Data Index: 5277859 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.2729. Min Act: -0.1700
Data Index: 8618811 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.3041. Min Act: -0.1700
Data Index: 794853 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.2104. Min Act: -0.1700
Data Index: 247816 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.1479. Min Act: -0.1700
Data Index: 4348232 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.1479. Min Act: -0.1700
Data Index: 5433272 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.1166. Min Act: -0.1700
Data Index: 508249 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.0854. Min Act: -0.1700
Data Index: 7799765 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.0854. Min Act: -0.1700
Data Index: 6926011 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.0854. Min Act: -0.1700
Data Index: 8603682 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.0541. Min Act: -0.1700
Data Index: 5503915 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1479. Min Range: -8.1479
Max Act: 7.0541. Min Act: -0.1700
Data Index: 1548488 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19