Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6400311 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.6871. Min Act: -0.1700
Data Index: 1189160 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.6559. Min Act: -0.1700
Data Index: 8154510 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.5934. Min Act: -0.1700
Data Index: 8505061 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.4996. Min Act: -0.1700
Data Index: 4499263 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.4371. Min Act: -0.1700
Data Index: 7430870 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.4684. Min Act: -0.1700
Data Index: 4825562 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.4059. Min Act: -0.1700
Data Index: 7430867 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.4059. Min Act: -0.1700
Data Index: 7642804 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3746. Min Act: -0.1700
Data Index: 945675 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3746. Min Act: -0.1700
Data Index: 8543593 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3746. Min Act: -0.1700
Data Index: 7936020 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3434. Min Act: -0.1700
Data Index: 3270617 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3121. Min Act: -0.1700
Data Index: 6775233 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3434. Min Act: -0.1700
Data Index: 4906153 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3121. Min Act: -0.1700
Data Index: 5608075 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.3121. Min Act: -0.1700
Data Index: 1147399 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.2809. Min Act: -0.1700
Data Index: 1872757 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.2809. Min Act: -0.1700
Data Index: 3562774 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7809. Min Range: -4.7809
Max Act: 4.2809. Min Act: -0.1700
Data Index: 8295900 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19