Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4788 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1493891 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1619. Min Act: -0.0000

Data Index: 179513 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1550396 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1647. Min Act: -0.0000

Data Index: 932291 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1111252 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1374593 (Python Code)

Max Activating Token Index: 212

Text #6

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1370536 (Python Code)

Max Activating Token Index: 570

Text #7

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1419. Min Act: -0.0000

Data Index: 699836 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1560140 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1340. Min Act: -0.0000

Data Index: 347422 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1561979 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1609021 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1508517 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1337. Min Act: -0.0000

Data Index: 155404 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1334. Min Act: -0.0000

Data Index: 983936 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1326. Min Act: -0.0000

Data Index: 796165 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1314. Min Act: -0.0000

Data Index: 563912 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1177741 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1299. Min Act: -0.0000

Data Index: 616117 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1652100 (Python Code)

Max Activating Token Index: 176