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

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

Neuron 3464 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1219477 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1466. Min Act: -0.0000

Data Index: 441944 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1492. Min Act: -0.0000

Data Index: 874509 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1399. Min Act: -0.0000

Data Index: 207962 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1455. Min Act: -0.0000

Data Index: 886199 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1406. Min Act: -0.0000

Data Index: 344267 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1035882 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1399. Min Act: -0.0000

Data Index: 96992 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1378. Min Act: -0.0000

Data Index: 249015 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1343. Min Act: -0.0000

Data Index: 476707 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1327. Min Act: -0.0000

Data Index: 598647 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1352. Min Act: 0.0000

Data Index: 946605 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1388. Min Act: -0.0000

Data Index: 201472 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1327. Min Act: -0.0000

Data Index: 126693 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1359. Min Act: -0.0000

Data Index: 137787 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1259. Min Act: -0.0000

Data Index: 858054 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1296. Min Act: -0.0000

Data Index: 384408 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1282. Min Act: -0.0000

Data Index: 262804 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1036156 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1096867 (C4 (Web Text))

Max Activating Token Index: 762