Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1382700 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1493. Min Act: -0.0001

Data Index: 782913 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1397194 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1481683 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1223. Min Act: -0.0001

Data Index: 927018 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1335. Min Act: -0.0001

Data Index: 673416 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1434. Min Act: -0.0001

Data Index: 412401 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1386577 (Python Code)

Max Activating Token Index: 687

Text #8

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1367588 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1392. Min Act: -0.0001

Data Index: 224554 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1266. Min Act: -0.0001

Data Index: 171832 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1262. Min Act: -0.0001

Data Index: 946440 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1268. Min Act: -0.0001

Data Index: 931482 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1112. Min Act: -0.0001

Data Index: 217056 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1368885 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1223. Min Act: -0.0001

Data Index: 718528 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1552689 (Python Code)

Max Activating Token Index: 514

Text #17

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1327831 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1289. Min Act: -0.0001

Data Index: 681686 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1552129 (Python Code)

Max Activating Token Index: 647