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

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

Neuron 2224 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2620. Min Range: -1.2620

Max Act: 1.2620. Min Act: -0.0000

Data Index: 858857 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.2620. Min Range: -1.2620

Max Act: 1.1581. Min Act: -0.0000

Data Index: 30994 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.2620. Min Range: -1.2620

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1172918 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.2620. Min Range: -1.2620

Max Act: 1.0080. Min Act: -0.0000

Data Index: 156938 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.2620. Min Range: -1.2620

Max Act: 1.1682. Min Act: -0.0000

Data Index: 689586 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.2620. Min Range: -1.2620

Max Act: 1.0419. Min Act: -0.0000

Data Index: 820595 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9665. Min Act: -0.0000

Data Index: 215978 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1124641 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9280. Min Act: -0.0000

Data Index: 913917 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1283224 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1052477 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1284500 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.8482. Min Act: -0.0000

Data Index: 599444 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9009. Min Act: -0.0000

Data Index: 416785 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.8423. Min Act: -0.0000

Data Index: 652564 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.8353. Min Act: -0.0000

Data Index: 335364 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.8874. Min Act: -0.0000

Data Index: 780753 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1656611 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1071736 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.2620. Min Range: -1.2620

Max Act: 0.8684. Min Act: -0.0000

Data Index: 866707 (C4 (Web Text))

Max Activating Token Index: 876