Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.3103. Min Act: -0.1700
Data Index: 8748844 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.2791. Min Act: -0.1700
Data Index: 5795238 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.2478. Min Act: -0.1700
Data Index: 1052754 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.1541. Min Act: -0.1700
Data Index: 7446109 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.1541. Min Act: -0.1700
Data Index: 1430611 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.1541. Min Act: -0.1700
Data Index: 1521903 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.0916. Min Act: -0.1700
Data Index: 1760561 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.0291. Min Act: -0.1700
Data Index: 4771298 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3103. Min Range: -6.3103
Max Act: 6.0291. Min Act: -0.1700
Data Index: 1993266 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9666. Min Act: -0.1700
Data Index: 4426696 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9353. Min Act: -0.1700
Data Index: 8167857 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9353. Min Act: -0.1700
Data Index: 1502556 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9041. Min Act: -0.1700
Data Index: 4618039 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9041. Min Act: -0.1700
Data Index: 2584611 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9041. Min Act: -0.1700
Data Index: 7617933 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9041. Min Act: -0.1700
Data Index: 5015595 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.9041. Min Act: -0.1700
Data Index: 4666195 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.8728. Min Act: -0.1700
Data Index: 2584928 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.8728. Min Act: -0.1700
Data Index: 4886955 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3103. Min Range: -6.3103
Max Act: 5.8728. Min Act: -0.1700
Data Index: 2197298 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19