Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1729. Min Range: -5.1729
Max Act: 5.1729. Min Act: -0.1700
Data Index: 6312911 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1729. Min Range: -5.1729
Max Act: 5.1104. Min Act: -0.1700
Data Index: 2774445 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1729. Min Range: -5.1729
Max Act: 5.0479. Min Act: -0.1700
Data Index: 6228040 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1729. Min Range: -5.1729
Max Act: 5.0479. Min Act: -0.1700
Data Index: 398085 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1729. Min Range: -5.1729
Max Act: 5.0479. Min Act: -0.1700
Data Index: 6136252 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9854. Min Act: -0.1700
Data Index: 5362786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9854. Min Act: -0.1700
Data Index: 1790366 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9854. Min Act: -0.1700
Data Index: 7700683 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9229. Min Act: -0.1700
Data Index: 1447993 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9229. Min Act: -0.1700
Data Index: 6206121 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9229. Min Act: -0.1700
Data Index: 219183 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9229. Min Act: -0.1700
Data Index: 5951378 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9229. Min Act: -0.1700
Data Index: 8627728 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.9229. Min Act: -0.1700
Data Index: 6250886 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.8917. Min Act: -0.1700
Data Index: 545731 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.8604. Min Act: -0.1700
Data Index: 7799736 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.8292. Min Act: -0.1700
Data Index: 6197059 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.8292. Min Act: -0.1700
Data Index: 4665643 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.7979. Min Act: -0.1700
Data Index: 6550878 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1729. Min Range: -5.1729
Max Act: 4.7667. Min Act: -0.1700
Data Index: 5181085 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19