Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.3969. Min Range: -4.3969

Max Act: 4.3969. Min Act: -0.0000

Data Index: 1719882 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.9941. Min Act: -0.0000

Data Index: 148262 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 4.3969. Min Range: -4.3969

Max Act: 3.3956. Min Act: -0.0000

Data Index: 1778626 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.8235. Min Act: -0.0000

Data Index: 1178466 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.5488. Min Act: -0.0000

Data Index: 297902 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.6367. Min Act: -0.0000

Data Index: 651204 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.5883. Min Act: -0.0000

Data Index: 1560940 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.8008. Min Act: -0.0000

Data Index: 91758 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.6792. Min Act: -0.0000

Data Index: 320787 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.7743. Min Act: -0.0000

Data Index: 641006 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.4900. Min Act: -0.0000

Data Index: 1855214 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.3548. Min Act: -0.0000

Data Index: 366228 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.6003. Min Act: -0.0000

Data Index: 1527075 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.3447. Min Act: -0.0000

Data Index: 453569 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.3268. Min Act: -0.0000

Data Index: 836076 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.4252. Min Act: -0.0000

Data Index: 367197 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.5308. Min Act: -0.0000

Data Index: 291215 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.3909. Min Act: -0.0000

Data Index: 1597558 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.5008. Min Act: -0.0000

Data Index: 1969427 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 4.3969. Min Range: -4.3969

Max Act: 2.3570. Min Act: -0.0000

Data Index: 61432 (The Pile)

Max Activating Token Index: 527