Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1179 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1139035 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8405. Min Act: -0.0000

Data Index: 499843 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8906. Min Act: -0.0000

Data Index: 290551 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1246137 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7767. Min Act: -0.0000

Data Index: 48606 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7038. Min Act: -0.0000

Data Index: 896635 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1306349 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7439. Min Act: -0.0000

Data Index: 756369 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1018791 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1325927 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1166027 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1175195 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1300686 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6865. Min Act: 0.0000

Data Index: 167574 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1274591 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6620. Min Act: -0.0000

Data Index: 864577 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6624. Min Act: -0.0000

Data Index: 247389 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6644. Min Act: -0.0000

Data Index: 763340 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7059. Min Act: -0.0000

Data Index: 771066 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.6609. Min Act: -0.0000

Data Index: 96711 (C4 (Web Text))

Max Activating Token Index: 505