Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 359 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.3200. Min Act: -0.0000

Data Index: 824772 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2632. Min Act: -0.0000

Data Index: 901246 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2581. Min Act: -0.0000

Data Index: 619841 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1501754 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2542. Min Act: -0.0000

Data Index: 916309 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1592482 (Python Code)

Max Activating Token Index: 532

Text #6

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2688. Min Act: -0.0000

Data Index: 184058 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1611984 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1208049 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2462. Min Act: -0.0000

Data Index: 227088 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1212660 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1530389 (Python Code)

Max Activating Token Index: 724

Text #12

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2283. Min Act: -0.0000

Data Index: 667133 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2167. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2202. Min Act: -0.0000

Data Index: 391596 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1150962 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2382. Min Act: -0.0000

Data Index: 233144 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2367. Min Act: -0.0000

Data Index: 876285 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1585858 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 0.3200. Min Range: -0.3200

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1646076 (Python Code)

Max Activating Token Index: 858