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

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

Neuron 153 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0360. Min Act: -0.0000

Data Index: 35039 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0960. Min Act: -0.0000

Data Index: 484392 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0619. Min Act: -0.0000

Data Index: 756338 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0103. Min Act: -0.0000

Data Index: 667542 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0505. Min Act: 0.0000

Data Index: 1292784 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0119. Min Act: -0.0000

Data Index: 537920 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0790. Min Act: -0.0000

Data Index: 151742 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.0960. Min Range: -1.0960

Max Act: 1.0019. Min Act: -0.0000

Data Index: 324248 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1184132 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9820. Min Act: -0.0000

Data Index: 957601 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1100170 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9282. Min Act: 0.0000

Data Index: 592566 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.8900. Min Act: -0.0000

Data Index: 823010 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1136187 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9173. Min Act: -0.0000

Data Index: 617266 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1237405 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.9003. Min Act: -0.0000

Data Index: 1216198 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.8981. Min Act: -0.0000

Data Index: 277967 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.8924. Min Act: -0.0000

Data Index: 342966 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.0960. Min Range: -1.0960

Max Act: 0.8917. Min Act: -0.0000

Data Index: 680193 (C4 (Web Text))

Max Activating Token Index: 852