Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2295 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0000

Data Index: 418150 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0366. Min Act: -0.0000

Data Index: 385700 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0338. Min Act: -0.0000

Data Index: 316871 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1614453 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0336. Min Act: -0.0000

Data Index: 1404862 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0331. Min Act: -0.0000

Data Index: 566816 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1607618 (Python Code)

Max Activating Token Index: 880

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1479499 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0302. Min Act: -0.0000

Data Index: 31507 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1093715 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1164102 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0289. Min Act: -0.0000

Data Index: 1506553 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0274. Min Act: -0.0000

Data Index: 914187 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0273. Min Act: -0.0000

Data Index: 908657 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1413423 (Python Code)

Max Activating Token Index: 289

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1438121 (Python Code)

Max Activating Token Index: 299

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1423669 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0269. Min Act: -0.0000

Data Index: 132271 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1643180 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1645307 (Python Code)

Max Activating Token Index: 254