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

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

Neuron 4317 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0000

Data Index: 954027 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1442. Min Act: -0.0000

Data Index: 103998 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1379. Min Act: -0.0000

Data Index: 162904 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1098218 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1444. Min Act: -0.0000

Data Index: 842808 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1391. Min Act: -0.0000

Data Index: 389795 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1332. Min Act: -0.0000

Data Index: 976234 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1042652 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1275271 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1232. Min Act: -0.0000

Data Index: 568982 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1098. Min Act: -0.0000

Data Index: 114445 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1211. Min Act: -0.0000

Data Index: 23767 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1151. Min Act: -0.0000

Data Index: 809753 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1237. Min Act: -0.0000

Data Index: 305963 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1294. Min Act: -0.0000

Data Index: 282006 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1260. Min Act: -0.0000

Data Index: 374967 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1235936 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1200. Min Act: -0.0000

Data Index: 389186 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1269. Min Act: -0.0000

Data Index: 85515 (C4 (Web Text))

Max Activating Token Index: 414