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

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

Neuron 2694 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2891. Min Act: 0.0000

Data Index: 302763 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1310894 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2428. Min Act: -0.0000

Data Index: 123198 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2490. Min Act: 0.0000

Data Index: 1231028 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1365519 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2365. Min Act: -0.0000

Data Index: 83350 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2353. Min Act: -0.0000

Data Index: 420080 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1596346 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1287558 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1647934 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1493716 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1580561 (Python Code)

Max Activating Token Index: 106

Text #12

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1391120 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2074. Min Act: -0.0000

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1907. Min Act: -0.0000

Data Index: 850854 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1284545 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1390060 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2029. Min Act: -0.0000

Data Index: 197549 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1952. Min Act: -0.0000

Data Index: 685904 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1926. Min Act: -0.0000

Data Index: 560188 (C4 (Web Text))

Max Activating Token Index: 492