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

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

Neuron 2096 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1208600 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1242185 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1191090 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1495. Min Act: -0.0001

Data Index: 315869 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1704. Min Act: -0.0001

Data Index: 951971 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1604. Min Act: -0.0001

Data Index: 671334 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1619. Min Act: -0.0001

Data Index: 406947 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1450. Min Act: -0.0001

Data Index: 281329 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1542. Min Act: -0.0001

Data Index: 740816 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1428. Min Act: -0.0001

Data Index: 917428 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1220718 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1504. Min Act: -0.0001

Data Index: 22055 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1459. Min Act: -0.0001

Data Index: 280115 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1314032 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1284. Min Act: -0.0001

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1307471 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1202. Min Act: -0.0001

Data Index: 505593 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1161. Min Act: -0.0001

Data Index: 853015 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1357. Min Act: -0.0001

Data Index: 820293 (C4 (Web Text))

Max Activating Token Index: 1021