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

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

Neuron 4561 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: 0.2085. Min Range: -0.2085

Max Act: 0.2085. Min Act: -0.0000

Data Index: 945608 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1701. Min Act: -0.0000

Data Index: 584983 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1545. Min Act: 0.0000

Data Index: 648408 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1535. Min Act: -0.0000

Data Index: 15047 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1099928 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1414. Min Act: -0.0000

Data Index: 896151 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1460. Min Act: 0.0000

Data Index: 1212702 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1070402 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1411. Min Act: 0.0000

Data Index: 1065398 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1411. Min Act: -0.0000

Data Index: 691450 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1334. Min Act: -0.0000

Data Index: 601896 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1408. Min Act: -0.0000

Data Index: 947540 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1387. Min Act: -0.0000

Data Index: 601013 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1263. Min Act: -0.0000

Data Index: 27053 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1330. Min Act: -0.0000

Data Index: 790395 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1307. Min Act: -0.0000

Data Index: 728185 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1281. Min Act: -0.0000

Data Index: 931984 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1246. Min Act: -0.0000

Data Index: 961499 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1273. Min Act: -0.0000

Data Index: 34568 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.2085. Min Range: -0.2085

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1283866 (C4 (Web Text))

Max Activating Token Index: 978