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

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

Neuron 3229 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.8452. Min Act: -0.0000

Data Index: 648152 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.8416. Min Act: -0.0000

Data Index: 770700 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 3.0737. Min Range: -3.0737

Max Act: 3.0737. Min Act: -0.0000

Data Index: 1213318 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.7401. Min Act: -0.0000

Data Index: 561579 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.7285. Min Act: -0.0000

Data Index: 372268 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1204430 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1006194 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.5053. Min Act: -0.0000

Data Index: 977837 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.4113. Min Act: -0.0000

Data Index: 1283478 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.3629. Min Act: -0.0000

Data Index: 121324 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.3993. Min Act: -0.0000

Data Index: 1279711 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.1639. Min Act: -0.0000

Data Index: 1320416 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.3847. Min Act: -0.0000

Data Index: 196439 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.1298. Min Act: -0.0000

Data Index: 183438 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1110163 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.2286. Min Act: -0.0000

Data Index: 22606 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.1009. Min Act: -0.0000

Data Index: 353714 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.1909. Min Act: -0.0000

Data Index: 848697 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.0291. Min Act: -0.0000

Data Index: 525356 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 3.0737. Min Range: -3.0737

Max Act: 2.1278. Min Act: -0.0000

Data Index: 540032 (C4 (Web Text))

Max Activating Token Index: 769