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

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

Neuron 1145 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: 0.0370. Min Range: -0.0370

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1230133 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1192224 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1386080 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0355. Min Act: -0.0000

Data Index: 246292 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0354. Min Act: -0.0000

Data Index: 955062 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1197427 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1159859 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1095185 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1484407 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0315. Min Act: -0.0000

Data Index: 760492 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1554967 (Python Code)

Max Activating Token Index: 872

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1585979 (Python Code)

Max Activating Token Index: 982

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1223369 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0317. Min Act: -0.0000

Data Index: 317169 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0307. Min Act: -0.0000

Data Index: 1424035 (Python Code)

Max Activating Token Index: 1021

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1596220 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1443532 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1416390 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0300. Min Act: -0.0000

Data Index: 608133 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1624295 (Python Code)

Max Activating Token Index: 1004