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

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

Neuron 5045 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.3409. Min Act: -0.0000

Data Index: 736227 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1357. Min Act: -0.0000

Data Index: 375358 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1336. Min Act: -0.0000

Data Index: 351952 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1328801 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0610. Min Act: -0.0000

Data Index: 951755 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0566. Min Act: -0.0000

Data Index: 903374 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0466. Min Act: -0.0000

Data Index: 203824 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9812. Min Act: -0.0000

Data Index: 840618 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0896. Min Act: -0.0000

Data Index: 847300 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1139227 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1337263 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9781. Min Act: -0.0000

Data Index: 620179 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1272951 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9543. Min Act: -0.0000

Data Index: 233717 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0359. Min Act: -0.0000

Data Index: 246041 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.3409. Min Range: -1.3409

Max Act: 1.0544. Min Act: -0.0000

Data Index: 951262 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9618. Min Act: -0.0000

Data Index: 960269 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9828. Min Act: -0.0000

Data Index: 99675 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9422. Min Act: -0.0000

Data Index: 540217 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.3409. Min Range: -1.3409

Max Act: 0.9705. Min Act: -0.0000

Data Index: 16453 (C4 (Web Text))

Max Activating Token Index: 1021