Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 7364917 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 6260849 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 3807942 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 7364912 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0460. Min Act: -0.1700
Data Index: 7364915 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9835. Min Act: -0.1700
Data Index: 422774 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9835. Min Act: -0.1700
Data Index: 7580426 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 2104809 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 7110216 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9835. Min Act: -0.1700
Data Index: 6186042 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 7364927 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7767820 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 6857739 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7364906 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7364924 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8897. Min Act: -0.1700
Data Index: 1534595 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7238170 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8585. Min Act: -0.1700
Data Index: 6599418 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8585. Min Act: -0.1700
Data Index: 3788955 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8272. Min Act: -0.1700
Data Index: 734907 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19