Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.4025. Min Act: -0.1700
Data Index: 13786 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.3087. Min Act: -0.1700
Data Index: 4943211 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.3087. Min Act: -0.1700
Data Index: 5159486 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.3087. Min Act: -0.1700
Data Index: 2445459 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.2774. Min Act: -0.1700
Data Index: 4059786 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.1837. Min Act: -0.1700
Data Index: 2291740 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4025. Min Range: -4.4025
Max Act: 4.0587. Min Act: -0.1700
Data Index: 1550462 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9961. Min Act: -0.1700
Data Index: 6318345 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9649. Min Act: -0.1700
Data Index: 4763195 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9649. Min Act: -0.1700
Data Index: 1997268 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9649. Min Act: -0.1700
Data Index: 7229773 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9336. Min Act: -0.1700
Data Index: 8327117 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9336. Min Act: -0.1700
Data Index: 4973949 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9336. Min Act: -0.1700
Data Index: 7534107 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9024. Min Act: -0.1700
Data Index: 1200846 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9024. Min Act: -0.1700
Data Index: 6568390 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9024. Min Act: -0.1700
Data Index: 6719382 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.9336. Min Act: -0.1700
Data Index: 6369449 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.8711. Min Act: -0.1700
Data Index: 6887581 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4025. Min Range: -4.4025
Max Act: 3.8398. Min Act: -0.1700
Data Index: 4508865 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19