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

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

Neuron 2312 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4255. Min Range: -3.4255

Max Act: 3.3125. Min Act: -0.0000

Data Index: 26157 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 3.4255. Min Range: -3.4255

Max Act: 3.4255. Min Act: -0.0000

Data Index: 750791 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.6681. Min Act: -0.0000

Data Index: 1138879 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 3.4255. Min Range: -3.4255

Max Act: 3.2250. Min Act: -0.0000

Data Index: 763523 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 3.4255. Min Range: -3.4255

Max Act: 3.1771. Min Act: -0.0000

Data Index: 594492 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.9944. Min Act: -0.0000

Data Index: 1207381 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 3.4255. Min Range: -3.4255

Max Act: 3.1048. Min Act: -0.0000

Data Index: 1316889 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.7775. Min Act: -0.0000

Data Index: 414082 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.5980. Min Act: -0.0000

Data Index: 892008 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.9947. Min Act: -0.0000

Data Index: 890077 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.9995. Min Act: -0.0000

Data Index: 336339 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.5625. Min Act: -0.0000

Data Index: 482454 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.4075. Min Act: -0.0000

Data Index: 1082470 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.6991. Min Act: -0.0000

Data Index: 272877 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.9431. Min Act: -0.0000

Data Index: 1243431 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.7681. Min Act: -0.0000

Data Index: 662030 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.7179. Min Act: -0.0000

Data Index: 1263912 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.5873. Min Act: -0.0000

Data Index: 790097 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.7483. Min Act: -0.0000

Data Index: 529096 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 3.4255. Min Range: -3.4255

Max Act: 2.8910. Min Act: -0.0000

Data Index: 1105516 (C4 (Web Text))

Max Activating Token Index: 387