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

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

Neuron 696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1251517 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.9319. Min Act: -0.0000

Data Index: 216278 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8030. Min Act: -0.0000

Data Index: 747704 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7519. Min Act: -0.0000

Data Index: 360456 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7951. Min Act: -0.0000

Data Index: 635246 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1469927 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1628227 (Python Code)

Max Activating Token Index: 797

Text #7

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1300970 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1339487 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6439. Min Act: -0.0000

Data Index: 41879 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1410236 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7006. Min Act: -0.0000

Data Index: 497532 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1513401 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1482953 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1609551 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1401137 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1089037 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6063. Min Act: -0.0001

Data Index: 1553032 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1540939 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6247. Min Act: -0.0000

Data Index: 501916 (C4 (Web Text))

Max Activating Token Index: 78