Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3838 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.2883. Min Range: -5.2883

Max Act: 5.2883. Min Act: -0.0000

Data Index: 1165474 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 5.2883. Min Range: -5.2883

Max Act: 4.4681. Min Act: -0.0001

Data Index: 358055 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.8933. Min Act: -0.0001

Data Index: 911171 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.4573. Min Act: -0.0001

Data Index: 248726 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 5.2883. Min Range: -5.2883

Max Act: 4.1374. Min Act: -0.0001

Data Index: 874534 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.3353. Min Act: -0.0001

Data Index: 1097600 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.9530. Min Act: -0.0000

Data Index: 1355320 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.3575. Min Act: -0.0000

Data Index: 58233 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.0847. Min Act: -0.0000

Data Index: 979829 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.0864. Min Act: 0.0000

Data Index: 1059365 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.0643. Min Act: -0.0000

Data Index: 746072 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.8798. Min Act: -0.0001

Data Index: 845563 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 5.2883. Min Range: -5.2883

Max Act: 3.1333. Min Act: -0.0001

Data Index: 685620 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.7366. Min Act: -0.0001

Data Index: 353988 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.4713. Min Act: -0.0001

Data Index: 298553 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.7179. Min Act: -0.0001

Data Index: 239020 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.4483. Min Act: -0.0000

Data Index: 236999 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.5657. Min Act: -0.0000

Data Index: 110275 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.6285. Min Act: -0.0000

Data Index: 704224 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 5.2883. Min Range: -5.2883

Max Act: 2.3502. Min Act: -0.0001

Data Index: 278252 (C4 (Web Text))

Max Activating Token Index: 573