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

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

Neuron 671 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: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 675083 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1396. Min Act: -0.0001

Data Index: 555897 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1344. Min Act: -0.0001

Data Index: 409972 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1403. Min Act: -0.0001

Data Index: 478773 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1103946 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1225. Min Act: -0.0001

Data Index: 642780 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1352566 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1369. Min Act: -0.0001

Data Index: 499794 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1210168 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1184. Min Act: -0.0001

Data Index: 546637 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1037432 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1363. Min Act: -0.0001

Data Index: 140346 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1207. Min Act: -0.0001

Data Index: 941574 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1429. Min Act: -0.0001

Data Index: 764760 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1266. Min Act: -0.0001

Data Index: 431666 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1097961 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1231. Min Act: -0.0001

Data Index: 527409 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1148. Min Act: -0.0001

Data Index: 488938 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1197005 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1255. Min Act: -0.0001

Data Index: 617272 (C4 (Web Text))

Max Activating Token Index: 337