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

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

Neuron 3622 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2711. Min Act: -0.0000

Data Index: 26388 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1387819 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1599372 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1424031 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1531148 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1400900 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1541740 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2147. Min Act: 0.0001

Data Index: 1361957 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2026. Min Act: 0.0000

Data Index: 1593295 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2166. Min Act: 0.0000

Data Index: 1504913 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2248. Min Act: 0.0001

Data Index: 1613322 (Python Code)

Max Activating Token Index: 806

Text #11

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2164. Min Act: 0.0000

Data Index: 1536829 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1589002 (Python Code)

Max Activating Token Index: 523

Text #13

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1520535 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1435471 (Python Code)

Max Activating Token Index: 926

Text #15

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2105. Min Act: 0.0001

Data Index: 1639614 (Python Code)

Max Activating Token Index: 972

Text #16

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1455350 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2101. Min Act: 0.0000

Data Index: 1557263 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1585605 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 0.2711. Min Range: -0.2711

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1573441 (Python Code)

Max Activating Token Index: 652