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

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

Neuron 2673 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: 1.1460. Min Range: -1.1460

Max Act: 1.1460. Min Act: -0.0000

Data Index: 624515 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8825. Min Act: -0.0000

Data Index: 8261 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8211. Min Act: -0.0000

Data Index: 918213 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7965. Min Act: -0.0000

Data Index: 148891 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7936. Min Act: -0.0000

Data Index: 320489 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7636. Min Act: -0.0000

Data Index: 665767 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1146520 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7135. Min Act: -0.0000

Data Index: 602165 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7541. Min Act: -0.0000

Data Index: 574181 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7099. Min Act: -0.0000

Data Index: 239111 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7299. Min Act: -0.0000

Data Index: 891932 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7353. Min Act: -0.0000

Data Index: 178591 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6577. Min Act: -0.0000

Data Index: 103898 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6236. Min Act: -0.0000

Data Index: 834895 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1165311 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6108. Min Act: -0.0000

Data Index: 45542 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6249. Min Act: -0.0000

Data Index: 615638 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.5879. Min Act: -0.0000

Data Index: 573147 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6290. Min Act: -0.0000

Data Index: 562701 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.6600. Min Act: -0.0000

Data Index: 973017 (C4 (Web Text))

Max Activating Token Index: 194