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

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

Neuron 4308 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: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0000

Data Index: 180407 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1424. Min Act: -0.0000

Data Index: 431296 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1332. Min Act: -0.0000

Data Index: 728559 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1274. Min Act: -0.0000

Data Index: 62809 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1236. Min Act: -0.0000

Data Index: 709634 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1163. Min Act: -0.0000

Data Index: 926292 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1154. Min Act: -0.0000

Data Index: 489459 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1065. Min Act: -0.0000

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1033. Min Act: -0.0000

Data Index: 295677 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1001. Min Act: -0.0000

Data Index: 485342 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0968. Min Act: -0.0000

Data Index: 935870 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0987. Min Act: -0.0000

Data Index: 458153 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1290617 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1080744 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0759. Min Act: -0.0000

Data Index: 576891 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1351502 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1140946 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0948. Min Act: -0.0000

Data Index: 420747 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0877. Min Act: -0.0000

Data Index: 505574 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0912. Min Act: -0.0000

Data Index: 165051 (C4 (Web Text))

Max Activating Token Index: 656