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

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

Neuron 3371 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1619385 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5959. Min Act: -0.0000

Data Index: 851697 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1544624 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1554829 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1591185 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5920. Min Act: -0.0000

Data Index: 70733 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1446597 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1376592 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1618281 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1452235 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5264. Min Act: -0.0000

Data Index: 209862 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5582. Min Act: -0.0000

Data Index: 181026 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1613187 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5385. Min Act: -0.0000

Data Index: 196992 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1154346 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1239192 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5289. Min Act: -0.0001

Data Index: 1538953 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5144. Min Act: -0.0000

Data Index: 775056 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5257. Min Act: -0.0000

Data Index: 231908 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1545588 (Python Code)

Max Activating Token Index: 1008