Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 293 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0347. Min Act: -0.0002

Data Index: 688300 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0348. Min Act: -0.0001

Data Index: 936837 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0309. Min Act: -0.0002

Data Index: 65913 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1409019 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1451226 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0287. Min Act: -0.0001

Data Index: 87337 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1381109 (Python Code)

Max Activating Token Index: 71

Text #7

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1612206 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0282. Min Act: -0.0001

Data Index: 974471 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1617327 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1207602 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0271. Min Act: -0.0001

Data Index: 275460 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0276. Min Act: -0.0001

Data Index: 909250 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0250. Min Act: -0.0001

Data Index: 415536 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1560139 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0278. Min Act: -0.0002

Data Index: 463339 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1629575 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0303. Min Act: -0.0002

Data Index: 19648 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1637197 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.0348. Min Range: -0.0348

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1086059 (C4 (Web Text))

Max Activating Token Index: 48