Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2479. Min Range: -8.2479
Max Act: 8.2479. Min Act: -0.1700
Data Index: 4652104 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.9979. Min Act: -0.1700
Data Index: 4448421 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.9979. Min Act: -0.1700
Data Index: 2565847 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.9354. Min Act: -0.1700
Data Index: 5632211 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.9042. Min Act: -0.1700
Data Index: 2572259 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.7792. Min Act: -0.1700
Data Index: 6805363 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6854. Min Act: -0.1700
Data Index: 4144065 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.7167. Min Act: -0.1700
Data Index: 4411726 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6854. Min Act: -0.1700
Data Index: 8829107 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6542. Min Act: -0.1700
Data Index: 8163815 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6229. Min Act: -0.1700
Data Index: 305434 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6229. Min Act: -0.1700
Data Index: 3992737 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6229. Min Act: -0.1700
Data Index: 5396036 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6229. Min Act: -0.1700
Data Index: 3865761 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.6229. Min Act: -0.1700
Data Index: 1402991 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.5604. Min Act: -0.1700
Data Index: 91758 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.5917. Min Act: -0.1700
Data Index: 8465449 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.5917. Min Act: -0.1700
Data Index: 1359533 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.5917. Min Act: -0.1700
Data Index: 2931952 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2479. Min Range: -8.2479
Max Act: 7.5604. Min Act: -0.1700
Data Index: 1580583 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19