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

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

Neuron 1640 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: 4.1205. Min Range: -4.1205

Max Act: 3.9914. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 4.1205. Min Range: -4.1205

Max Act: 4.1205. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 4.1205. Min Range: -4.1205

Max Act: 3.5212. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.8249. Min Act: -0.0000

Data Index: 1590360 (Python Code)

Max Activating Token Index: 876

Text #4

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.1803. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.6494. Min Act: -0.0000

Data Index: 1609569 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.2971. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.3520. Min Act: -0.0000

Data Index: 1457967 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.3210. Min Act: -0.0000

Data Index: 1371055 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.0796. Min Act: -0.0000

Data Index: 1470958 (Python Code)

Max Activating Token Index: 354

Text #10

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.0481. Min Act: -0.0000

Data Index: 1582320 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.1548. Min Act: -0.0000

Data Index: 1582599 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.2454. Min Act: -0.0000

Data Index: 1655074 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.0034. Min Act: -0.0000

Data Index: 1442701 (Python Code)

Max Activating Token Index: 225

Text #14

Max Range: 4.1205. Min Range: -4.1205

Max Act: 2.2133. Min Act: -0.0000

Data Index: 1412168 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 4.1205. Min Range: -4.1205

Max Act: 1.8669. Min Act: -0.0000

Data Index: 1589159 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 4.1205. Min Range: -4.1205

Max Act: 1.7217. Min Act: -0.0000

Data Index: 1434550 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 4.1205. Min Range: -4.1205

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1459339 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 4.1205. Min Range: -4.1205

Max Act: 1.8947. Min Act: -0.0000

Data Index: 1428309 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 4.1205. Min Range: -4.1205

Max Act: 1.6270. Min Act: -0.0000

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 824