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

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

Neuron 2644 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1534671 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1536572 (Python Code)

Max Activating Token Index: 486

Text #2

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1593783 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1442120 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1376329 (Python Code)

Max Activating Token Index: 300

Text #5

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1551629 (Python Code)

Max Activating Token Index: 562

Text #6

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1174. Min Act: -0.0001

Data Index: 970933 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1639896 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1253. Min Act: -0.0001

Data Index: 142859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1656259 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1192. Min Act: -0.0001

Data Index: 584149 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1568530 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1550495 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1194. Min Act: -0.0001

Data Index: 606329 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1643581 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1158. Min Act: -0.0001

Data Index: 11581 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1072. Min Act: -0.0001

Data Index: 124431 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1396205 (Python Code)

Max Activating Token Index: 949

Text #18

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1573451 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1655730 (Python Code)

Max Activating Token Index: 114