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

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

Neuron 2730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.9394. Min Act: -0.0000

Data Index: 1394772 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.8647. Min Act: -0.0000

Data Index: 1384654 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1447232 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1381902 (Python Code)

Max Activating Token Index: 701

Text #4

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1591088 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1404845 (Python Code)

Max Activating Token Index: 729

Text #6

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1638587 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.1150. Min Act: -0.0000

Data Index: 405615 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1370969 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1572910 (Python Code)

Max Activating Token Index: 998

Text #10

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1608511 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0303. Min Act: -0.0000

Data Index: 498174 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1514810 (Python Code)

Max Activating Token Index: 602

Text #13

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1542803 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1405949 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 1.9394. Min Range: -1.9394

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1447803 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 1.9394. Min Range: -1.9394

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1348460 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.9394. Min Range: -1.9394

Max Act: 0.9325. Min Act: -0.0000

Data Index: 85980 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.9394. Min Range: -1.9394

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1072511 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.9394. Min Range: -1.9394

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1423154 (Python Code)

Max Activating Token Index: 1022