Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5913. Min Act: -0.1700
Data Index: 1290395 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5913. Min Act: -0.1700
Data Index: 5450625 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5600. Min Act: -0.1700
Data Index: 7622276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5600. Min Act: -0.1697
Data Index: 83482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5288. Min Act: -0.1700
Data Index: 5402439 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5288. Min Act: -0.1700
Data Index: 3756363 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4975. Min Act: -0.1700
Data Index: 806981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5288. Min Act: -0.1700
Data Index: 8804024 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5600. Min Act: -0.1700
Data Index: 8348894 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.5288. Min Act: -0.1700
Data Index: 3249858 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4975. Min Act: -0.1700
Data Index: 6341704 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4975. Min Act: -0.1699
Data Index: 5403300 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4975. Min Act: -0.1700
Data Index: 4536001 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4975. Min Act: -0.1700
Data Index: 2231874 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4975. Min Act: -0.1698
Data Index: 3095263 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4663. Min Act: -0.1700
Data Index: 3880416 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4663. Min Act: -0.1700
Data Index: 1196856 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4663. Min Act: -0.1700
Data Index: 508490 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4663. Min Act: -0.1700
Data Index: 5412894 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5913. Min Range: -4.5913
Max Act: 4.4350. Min Act: -0.1699
Data Index: 7383942 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19