Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4634 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.7660. Min Act: -0.1700
Data Index: 8253060 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.6723. Min Act: -0.1700
Data Index: 6879143 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.6410. Min Act: -0.1700
Data Index: 4992860 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.7035. Min Act: -0.1700
Data Index: 945 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.6098. Min Act: -0.1700
Data Index: 6879141 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.6098. Min Act: -0.1700
Data Index: 6184072 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5785. Min Act: -0.1700
Data Index: 7191173 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5160. Min Act: -0.1700
Data Index: 5599348 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5473. Min Act: -0.1700
Data Index: 517319 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5785. Min Act: -0.1700
Data Index: 6184059 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5785. Min Act: -0.1700
Data Index: 4969395 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5473. Min Act: -0.1700
Data Index: 8253059 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5473. Min Act: -0.1700
Data Index: 2925684 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.5160. Min Act: -0.1700
Data Index: 7013774 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.4848. Min Act: -0.1700
Data Index: 5576392 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3326032 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.4535. Min Act: -0.1700
Data Index: 2089207 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.4535. Min Act: -0.1700
Data Index: 6093520 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.4535. Min Act: -0.1700
Data Index: 517321 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7660. Min Range: -4.7660
Max Act: 4.4535. Min Act: -0.1700
Data Index: 4969388 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19