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

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

Neuron 5474 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: 0.2811. Min Range: -0.2811

Max Act: 0.2693. Min Act: -0.0001

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1622219 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2717. Min Act: -0.0000

Data Index: 553278 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2670. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2463. Min Act: -0.0001

Data Index: 1057171 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1492543 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2388. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1544208 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2160. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2367. Min Act: -0.0000

Data Index: 116229 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2425. Min Act: -0.0000

Data Index: 647491 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1260513 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1540812 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1193013 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2137. Min Act: -0.0001

Data Index: 756243 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2076. Min Act: -0.0000

Data Index: 306597 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2025. Min Act: -0.0001

Data Index: 1443537 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2152. Min Act: -0.0001

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2172. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 291