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

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

Neuron 2139 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0001

Data Index: 685764 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1289243 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1598. Min Act: -0.0001

Data Index: 585621 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1441. Min Act: -0.0001

Data Index: 130917 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1402. Min Act: -0.0001

Data Index: 532748 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1216802 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1417. Min Act: -0.0001

Data Index: 384071 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1390. Min Act: -0.0001

Data Index: 838758 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1402. Min Act: -0.0001

Data Index: 459168 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1321114 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1331. Min Act: -0.0001

Data Index: 405340 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1198582 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1319. Min Act: -0.0001

Data Index: 786291 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1243889 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1343519 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1228. Min Act: -0.0001

Data Index: 772045 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1242. Min Act: -0.0001

Data Index: 542022 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1210. Min Act: -0.0002

Data Index: 657071 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1183. Min Act: -0.0001

Data Index: 291768 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1200. Min Act: -0.0001

Data Index: 119130 (C4 (Web Text))

Max Activating Token Index: 586