Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1981 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1982. Min Act: -0.0001

Data Index: 814590 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1469. Min Act: -0.0001

Data Index: 830479 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1463. Min Act: -0.0001

Data Index: 607458 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1392. Min Act: -0.0001

Data Index: 204874 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1388. Min Act: -0.0001

Data Index: 294179 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1338. Min Act: -0.0001

Data Index: 796300 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1363. Min Act: -0.0001

Data Index: 400204 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1362. Min Act: -0.0001

Data Index: 946643 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1335. Min Act: -0.0001

Data Index: 974456 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1313. Min Act: 0.0000

Data Index: 1221249 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1309. Min Act: -0.0001

Data Index: 314093 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1207. Min Act: -0.0001

Data Index: 973004 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1255. Min Act: -0.0001

Data Index: 548921 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1243. Min Act: -0.0001

Data Index: 663927 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1285. Min Act: -0.0001

Data Index: 886167 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1141. Min Act: -0.0001

Data Index: 230208 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1232. Min Act: -0.0001

Data Index: 902571 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1313682 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1273554 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1304078 (C4 (Web Text))

Max Activating Token Index: 421