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

Dataset: The Pile

Neuron 3839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2788. Min Act: -0.0000

Data Index: 460921 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.3323. Min Act: -0.0000

Data Index: 1101765 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2524. Min Act: -0.0000

Data Index: 545372 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1255498 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1597077 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2253. Min Act: -0.0000

Data Index: 340326 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2418. Min Act: -0.0000

Data Index: 1788913 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2362. Min Act: -0.0000

Data Index: 690800 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1940. Min Act: -0.0000

Data Index: 855217 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1540897 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.2245. Min Act: -0.0000

Data Index: 1317825 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1173. Min Act: -0.0000

Data Index: 763560 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1230. Min Act: -0.0000

Data Index: 602405 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1268600 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0132. Min Act: -0.0000

Data Index: 561906 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1606. Min Act: -0.0000

Data Index: 277408 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1856070 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0448. Min Act: -0.0000

Data Index: 359551 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 1.3323. Min Range: -1.3323

Max Act: 0.9968. Min Act: -0.0000

Data Index: 773210 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.3323. Min Range: -1.3323

Max Act: 1.0814. Min Act: -0.0000

Data Index: 34500 (The Pile)

Max Activating Token Index: 393