Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4310 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.5605. Min Act: -0.1700
Data Index: 5907448 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.5293. Min Act: -0.1700
Data Index: 3682957 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.5293. Min Act: -0.1700
Data Index: 723799 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.4355. Min Act: -0.1700
Data Index: 1465755 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.4043. Min Act: -0.1700
Data Index: 5602927 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.3730. Min Act: -0.1700
Data Index: 7242184 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.2793. Min Act: -0.1700
Data Index: 4776667 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.2480. Min Act: -0.1700
Data Index: 7996675 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.1543. Min Act: -0.1700
Data Index: 3947997 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.1855. Min Act: -0.1700
Data Index: 2538660 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.1543. Min Act: -0.1700
Data Index: 2059494 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.1230. Min Act: -0.1700
Data Index: 6121928 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.1543. Min Act: -0.1700
Data Index: 6550082 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.1543. Min Act: -0.1700
Data Index: 7471236 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1375581 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.0918. Min Act: -0.1700
Data Index: 6521030 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.0605. Min Act: -0.1700
Data Index: 6391575 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5605. Min Range: -6.5605
Max Act: 6.0605. Min Act: -0.1700
Data Index: 1877131 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5605. Min Range: -6.5605
Max Act: 5.9668. Min Act: -0.1700
Data Index: 5719650 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5605. Min Range: -6.5605
Max Act: 5.9668. Min Act: -0.1700
Data Index: 4077809 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19