Model: None
Dataset: The Pile
Neuron 2568 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1589488 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4192. Min Act: -0.1700
Data Index: 4787580 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3722. Min Act: -0.1700
Data Index: 7637052 (The Pile)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3722. Min Act: -0.1700
Data Index: 3552655 (The Pile)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3094. Min Act: -0.1700
Data Index: 4861302 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2937. Min Act: -0.1700
Data Index: 7298643 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2937. Min Act: -0.1700
Data Index: 7671 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2937. Min Act: -0.1700
Data Index: 6796631 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 9801980 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2780. Min Act: -0.1700
Data Index: 8559472 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2623. Min Act: -0.1700
Data Index: 6306383 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2465. Min Act: -0.1700
Data Index: 512885 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2308. Min Act: -0.1699
Data Index: 10763012 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2151. Min Act: -0.1700
Data Index: 8138330 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2151. Min Act: -0.1700
Data Index: 7523050 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.1994. Min Act: -0.1700
Data Index: 3325147 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.1994. Min Act: -0.1700
Data Index: 8897423 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.1994. Min Act: -0.1700
Data Index: 1245194 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.1994. Min Act: -0.1700
Data Index: 6642895 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.1836. Min Act: -0.1700
Data Index: 1128459 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19