Model: None
Dataset: The Pile
Neuron 2992 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.6300. Min Act: -0.1700
Data Index: 9084227 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5831. Min Act: -0.1700
Data Index: 5549075 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5518. Min Act: -0.1700
Data Index: 7939128 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.4734. Min Act: -0.1700
Data Index: 2721167 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.3479. Min Act: -0.1700
Data Index: 4158981 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.3166. Min Act: -0.1700
Data Index: 10507955 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.2851. Min Act: -0.1700
Data Index: 537499 (The Pile)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.2694. Min Act: -0.1700
Data Index: 431993 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.2694. Min Act: -0.1700
Data Index: 4546895 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6184520 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.2223. Min Act: -0.1700
Data Index: 76461 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1908. Min Act: -0.1700
Data Index: 5381002 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1908. Min Act: -0.1700
Data Index: 2731467 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1751. Min Act: -0.1700
Data Index: 2745160 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1751. Min Act: -0.1700
Data Index: 10600064 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1436. Min Act: -0.1700
Data Index: 9211622 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1436. Min Act: -0.1700
Data Index: 2543491 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1436. Min Act: -0.1700
Data Index: 5354041 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1278. Min Act: -0.1700
Data Index: 6737825 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.1121. Min Act: -0.1700
Data Index: 3628835 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19