Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0588. Min Range: -3.0588

Max Act: 3.0588. Min Act: -0.0001

Data Index: 776059 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.5552. Min Act: -0.0001

Data Index: 500714 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.5626. Min Act: -0.0001

Data Index: 1213587 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.5571. Min Act: -0.0000

Data Index: 228204 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.4297. Min Act: -0.0001

Data Index: 1296244 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.3225. Min Act: -0.0001

Data Index: 328487 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2692. Min Act: -0.0001

Data Index: 517887 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.3294. Min Act: -0.0001

Data Index: 819289 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.3162. Min Act: -0.0001

Data Index: 85491 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2034. Min Act: -0.0001

Data Index: 1349859 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1886. Min Act: -0.0000

Data Index: 685591 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2088. Min Act: -0.0001

Data Index: 254742 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2510. Min Act: -0.0000

Data Index: 608226 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1928. Min Act: -0.0000

Data Index: 1101192 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1103883 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.0975. Min Act: -0.0001

Data Index: 131121 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.0384. Min Act: -0.0000

Data Index: 698177 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1325. Min Act: -0.0000

Data Index: 541099 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.0692. Min Act: -0.0000

Data Index: 96737 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 3.0588. Min Range: -3.0588

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1266832 (C4 (Web Text))

Max Activating Token Index: 548