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

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

Neuron 630 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: 0.1977. Min Range: -0.1977

Max Act: 0.1977. Min Act: -0.0000

Data Index: 748958 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1970. Min Act: -0.0000

Data Index: 188892 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1737. Min Act: -0.0000

Data Index: 602990 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1866. Min Act: -0.0000

Data Index: 313770 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1355600 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1447. Min Act: -0.0000

Data Index: 461045 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1399. Min Act: -0.0000

Data Index: 450368 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1365. Min Act: -0.0000

Data Index: 576875 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1433. Min Act: -0.0000

Data Index: 768360 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1325. Min Act: -0.0000

Data Index: 702543 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1235. Min Act: -0.0000

Data Index: 757091 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1209. Min Act: -0.0000

Data Index: 6416 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1375894 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1302. Min Act: -0.0000

Data Index: 570810 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1333. Min Act: -0.0000

Data Index: 85141 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1231901 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1016831 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1123655 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1150. Min Act: -0.0000

Data Index: 907248 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1218829 (C4 (Web Text))

Max Activating Token Index: 700