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

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

Neuron 2478 in Layer 2

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: -0.0002

Data Index: 46760 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1479. Min Act: -0.0001

Data Index: 602578 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1408. Min Act: -0.0001

Data Index: 122090 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1090025 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1346. Min Act: -0.0001

Data Index: 923171 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1351. Min Act: -0.0002

Data Index: 918771 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1247704 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1004441 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1282. Min Act: -0.0001

Data Index: 188659 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1204. Min Act: -0.0002

Data Index: 585225 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1224. Min Act: -0.0001

Data Index: 889308 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1177. Min Act: -0.0001

Data Index: 66073 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1159. Min Act: -0.0002

Data Index: 673265 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1202. Min Act: -0.0001

Data Index: 652761 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1047696 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1006732 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1076. Min Act: -0.0001

Data Index: 385874 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1119. Min Act: -0.0001

Data Index: 634624 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1149. Min Act: -0.0002

Data Index: 359104 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1023. Min Act: -0.0002

Data Index: 499834 (C4 (Web Text))

Max Activating Token Index: 942