Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.2115. Min Act: -0.0000

Data Index: 730084 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1145564 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1042684 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1619. Min Act: -0.0001

Data Index: 783334 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1581. Min Act: -0.0000

Data Index: 117429 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1542. Min Act: -0.0001

Data Index: 13228 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1450. Min Act: -0.0000

Data Index: 124490 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1165531 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1486. Min Act: -0.0000

Data Index: 554317 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1285. Min Act: -0.0001

Data Index: 794528 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1407. Min Act: -0.0001

Data Index: 920979 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1423. Min Act: -0.0000

Data Index: 193176 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1359. Min Act: -0.0000

Data Index: 419093 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1185968 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1212563 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1341. Min Act: -0.0000

Data Index: 887458 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1346. Min Act: -0.0000

Data Index: 51426 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1323. Min Act: -0.0000

Data Index: 494582 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1303. Min Act: -0.0000

Data Index: 7139 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1017237 (C4 (Web Text))

Max Activating Token Index: 880