Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1917. Min Range: -6.1917
Max Act: 6.1917. Min Act: -0.1700
Data Index: 87162 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1917. Min Range: -6.1917
Max Act: 6.0979. Min Act: -0.1700
Data Index: 217033 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1917. Min Range: -6.1917
Max Act: 6.0667. Min Act: -0.1700
Data Index: 7947996 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1917. Min Range: -6.1917
Max Act: 6.0354. Min Act: -0.1700
Data Index: 6998015 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1917. Min Range: -6.1917
Max Act: 6.0042. Min Act: -0.1700
Data Index: 3766165 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.9729. Min Act: -0.1700
Data Index: 2104339 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.8479. Min Act: -0.1700
Data Index: 5954793 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.8167. Min Act: -0.1700
Data Index: 3718582 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.7542. Min Act: -0.1700
Data Index: 2012674 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.6917. Min Act: -0.1700
Data Index: 7625823 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.6292. Min Act: -0.1700
Data Index: 2401882 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.6292. Min Act: -0.1700
Data Index: 1866512 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5979. Min Act: -0.1700
Data Index: 5744566 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5979. Min Act: -0.1700
Data Index: 4329601 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5979. Min Act: -0.1700
Data Index: 25434 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5667. Min Act: -0.1700
Data Index: 2983154 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5667. Min Act: -0.1700
Data Index: 3977035 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5667. Min Act: -0.1700
Data Index: 2229026 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5667. Min Act: -0.1700
Data Index: 6000134 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1917. Min Range: -6.1917
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5789846 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19