Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.2602. Min Act: -0.1700
Data Index: 967765 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.1977. Min Act: -0.1700
Data Index: 611950 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.1664. Min Act: -0.1700
Data Index: 8704804 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.1039. Min Act: -0.1700
Data Index: 6322627 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.0727. Min Act: -0.1700
Data Index: 2008470 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.0727. Min Act: -0.1700
Data Index: 4341999 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.0414. Min Act: -0.1700
Data Index: 1934936 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2602. Min Range: -6.2602
Max Act: 6.0102. Min Act: -0.1700
Data Index: 8368070 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.9789. Min Act: -0.1700
Data Index: 7559174 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.9789. Min Act: -0.1700
Data Index: 7415503 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.9477. Min Act: -0.1700
Data Index: 3296438 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.9164. Min Act: -0.1700
Data Index: 8666795 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.9164. Min Act: -0.1700
Data Index: 2521339 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8852. Min Act: -0.1700
Data Index: 2486694 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8539. Min Act: -0.1700
Data Index: 1320678 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8539. Min Act: -0.1700
Data Index: 2667981 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8539. Min Act: -0.1700
Data Index: 4774439 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8539. Min Act: -0.1700
Data Index: 1992169 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8227. Min Act: -0.1700
Data Index: 7769802 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2602. Min Range: -6.2602
Max Act: 5.8227. Min Act: -0.1700
Data Index: 4936860 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19