Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6742. Min Act: -0.0000

Data Index: 991240 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1389177 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5816. Min Act: -0.0000

Data Index: 257569 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5749. Min Act: -0.0000

Data Index: 475291 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1661602 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1746904 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1443154 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1565685 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5391. Min Act: -0.0000

Data Index: 87988 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1959151 (The Pile)

Max Activating Token Index: 402

Text #10

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1554040 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1472659 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1550890 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1879018 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1160057 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1602940 (The Pile)

Max Activating Token Index: 484

Text #16

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1235370 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5050. Min Act: -0.0000

Data Index: 631451 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5047. Min Act: -0.0000

Data Index: 823413 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4883. Min Act: -0.0000

Data Index: 964357 (The Pile)

Max Activating Token Index: 141