Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2167. Min Range: -4.2167
Max Act: 4.2167. Min Act: -0.1700
Data Index: 8663461 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2167. Min Range: -4.2167
Max Act: 4.0917. Min Act: -0.1700
Data Index: 1054697 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2167. Min Range: -4.2167
Max Act: 4.0605. Min Act: -0.1700
Data Index: 3366350 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2167. Min Range: -4.2167
Max Act: 4.0605. Min Act: -0.1700
Data Index: 8663443 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9979. Min Act: -0.1700
Data Index: 7506749 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9667. Min Act: -0.1700
Data Index: 111655 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9667. Min Act: -0.1700
Data Index: 7604572 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9354. Min Act: -0.1700
Data Index: 7604567 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9354. Min Act: -0.1700
Data Index: 1054698 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9354. Min Act: -0.1700
Data Index: 5252876 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9041. Min Act: -0.1700
Data Index: 6137643 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.8729. Min Act: -0.1700
Data Index: 5974078 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1436596 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9041. Min Act: -0.1700
Data Index: 3523328 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9041. Min Act: -0.1700
Data Index: 495527 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9041. Min Act: -0.1700
Data Index: 8145523 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1581440 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.8729. Min Act: -0.1700
Data Index: 5826218 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.8729. Min Act: -0.1700
Data Index: 2669969 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2167. Min Range: -4.2167
Max Act: 3.8416. Min Act: -0.1700
Data Index: 6064885 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19