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

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

Neuron 1730 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: 0.1190. Min Range: -0.1190

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1382236 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1354742 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1031. Min Act: -0.0000

Data Index: 537170 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0878. Min Act: -0.0000

Data Index: 415246 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0682. Min Act: -0.0000

Data Index: 118812 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1374956 (Python Code)

Max Activating Token Index: 459

Text #6

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0827. Min Act: -0.0001

Data Index: 953956 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0738. Min Act: -0.0000

Data Index: 906162 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1019704 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0861. Min Act: -0.0000

Data Index: 472988 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0504. Min Act: -0.0000

Data Index: 135297 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0556. Min Act: -0.0000

Data Index: 244396 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0592. Min Act: -0.0000

Data Index: 859068 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0622. Min Act: -0.0000

Data Index: 652240 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1219648 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0542. Min Act: -0.0000

Data Index: 429497 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0622. Min Act: -0.0000

Data Index: 124403 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1550849 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0589. Min Act: -0.0000

Data Index: 260166 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0627. Min Act: -0.0000

Data Index: 977134 (C4 (Web Text))

Max Activating Token Index: 249