Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.5561. Min Act: -0.1700
Data Index: 7473042 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.4936. Min Act: -0.1700
Data Index: 2929246 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.4623. Min Act: -0.1700
Data Index: 6494213 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.4311. Min Act: -0.1700
Data Index: 7463645 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.3998. Min Act: -0.1700
Data Index: 2141005 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.3686. Min Act: -0.1700
Data Index: 8631395 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.3373. Min Act: -0.1700
Data Index: 5056482 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.3373. Min Act: -0.1700
Data Index: 6481147 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.3061. Min Act: -0.1700
Data Index: 313587 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.3373. Min Act: -0.1700
Data Index: 6654158 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2748. Min Act: -0.1700
Data Index: 1895671 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2748. Min Act: -0.1700
Data Index: 2906822 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2748. Min Act: -0.1700
Data Index: 7016826 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2748. Min Act: -0.1700
Data Index: 1303970 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2436. Min Act: -0.1700
Data Index: 4445968 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2436. Min Act: -0.1700
Data Index: 982715 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2436. Min Act: -0.1700
Data Index: 7521918 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2123. Min Act: -0.1700
Data Index: 8713911 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2123. Min Act: -0.1700
Data Index: 6993988 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5561. Min Range: -6.5561
Max Act: 6.2436. Min Act: -0.1700
Data Index: 1749486 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19