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

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

Neuron 4471 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8963. Min Act: -0.0000

Data Index: 495892 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6926. Min Act: -0.0000

Data Index: 944760 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6862. Min Act: -0.0000

Data Index: 833202 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7209. Min Act: -0.0001

Data Index: 986424 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1066669 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1188951 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4883. Min Act: -0.0001

Data Index: 540727 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6242. Min Act: -0.0000

Data Index: 270854 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7033. Min Act: -0.0000

Data Index: 487502 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6230. Min Act: -0.0000

Data Index: 384398 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1090039 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6152. Min Act: -0.0000

Data Index: 250521 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7009. Min Act: -0.0001

Data Index: 134227 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1207488 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5937. Min Act: -0.0001

Data Index: 515884 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5522. Min Act: -0.0000

Data Index: 991440 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1197746 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1171300 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6287. Min Act: -0.0000

Data Index: 459462 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1132278 (C4 (Web Text))

Max Activating Token Index: 207