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

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

Neuron 4567 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: 0.3104. Min Range: -0.3104

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1648779 (Python Code)

Max Activating Token Index: 444

Text #1

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2719. Min Act: -0.0000

Data Index: 17204 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1492051 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1581500 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1583980 (Python Code)

Max Activating Token Index: 1003

Text #5

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2361. Min Act: -0.0000

Data Index: 748353 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2395. Min Act: 0.0000

Data Index: 1560806 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1560412 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2447. Min Act: -0.0000

Data Index: 244095 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1381552 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1167256 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1620251 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1600469 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1557856 (Python Code)

Max Activating Token Index: 411

Text #14

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1618376 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1563045 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1374849 (Python Code)

Max Activating Token Index: 538

Text #17

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1487957 (Python Code)

Max Activating Token Index: 753

Text #18

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1633016 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1395480 (Python Code)

Max Activating Token Index: 941