Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1234 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5539. Min Range: -5.5539
Max Act: 5.5539. Min Act: -0.1700
Data Index: 4590724 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5539. Min Range: -5.5539
Max Act: 5.4914. Min Act: -0.1700
Data Index: 4666228 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5539. Min Range: -5.5539
Max Act: 5.4289. Min Act: -0.1700
Data Index: 1459902 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5539. Min Range: -5.5539
Max Act: 5.3039. Min Act: -0.1700
Data Index: 8407566 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5539. Min Range: -5.5539
Max Act: 5.0539. Min Act: -0.1700
Data Index: 8025149 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.9601. Min Act: -0.1700
Data Index: 2660948 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.9289. Min Act: -0.1700
Data Index: 7686682 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8976. Min Act: -0.1700
Data Index: 5542592 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8976. Min Act: -0.1700
Data Index: 4761646 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 7459439 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8664. Min Act: -0.1700
Data Index: 47070 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8664. Min Act: -0.1700
Data Index: 8778597 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 995840 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8351. Min Act: -0.1700
Data Index: 8523223 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 2834868 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 7185852 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.8039. Min Act: -0.1700
Data Index: 7607801 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.7726. Min Act: -0.1700
Data Index: 4826431 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.7726. Min Act: -0.1700
Data Index: 2958067 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5539. Min Range: -5.5539
Max Act: 4.7414. Min Act: -0.1700
Data Index: 4725271 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19