Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.7886. Min Act: -0.1700
Data Index: 3412651 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.7261. Min Act: -0.1700
Data Index: 3714595 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.7261. Min Act: -0.1700
Data Index: 2199621 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6948. Min Act: -0.1700
Data Index: 4203684 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6948. Min Act: -0.1700
Data Index: 1164794 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6636. Min Act: -0.1700
Data Index: 3107486 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6323. Min Act: -0.1700
Data Index: 6744948 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6636. Min Act: -0.1700
Data Index: 3983352 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6636. Min Act: -0.1700
Data Index: 627938 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6636. Min Act: -0.1700
Data Index: 2226476 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6636. Min Act: -0.1700
Data Index: 3170260 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6323. Min Act: -0.1700
Data Index: 7292607 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6323. Min Act: -0.1700
Data Index: 7518611 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6011. Min Act: -0.1700
Data Index: 5338050 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6011. Min Act: -0.1700
Data Index: 8781097 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6011. Min Act: -0.1700
Data Index: 8166707 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6011. Min Act: -0.1700
Data Index: 39735 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.6011. Min Act: -0.1700
Data Index: 3063726 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.5698. Min Act: -0.1700
Data Index: 4848790 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7886. Min Range: -5.7886
Max Act: 5.5698. Min Act: -0.1700
Data Index: 5811122 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19