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

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

Neuron 2545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1335350 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1449. Min Act: -0.0000

Data Index: 50515 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1495. Min Act: -0.0000

Data Index: 358625 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1385210 (Python Code)

Max Activating Token Index: 874

Text #4

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1455. Min Act: -0.0000

Data Index: 354515 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1611451 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1455. Min Act: -0.0000

Data Index: 845491 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1335. Min Act: -0.0000

Data Index: 464370 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1075005 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1243. Min Act: -0.0000

Data Index: 137389 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1300650 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1257. Min Act: -0.0000

Data Index: 523005 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1536887 (Python Code)

Max Activating Token Index: 733

Text #13

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1309116 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1084. Min Act: -0.0000

Data Index: 579458 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1637683 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1504354 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1078. Min Act: -0.0000

Data Index: 788044 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1108. Min Act: -0.0000

Data Index: 852522 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1245737 (C4 (Web Text))

Max Activating Token Index: 649