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

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

Neuron 770 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0001

Data Index: 563386 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1319. Min Act: -0.0001

Data Index: 615333 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1186. Min Act: -0.0001

Data Index: 411737 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1015. Min Act: -0.0001

Data Index: 399419 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1053. Min Act: -0.0001

Data Index: 886523 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1059. Min Act: -0.0001

Data Index: 259147 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0989. Min Act: -0.0001

Data Index: 926680 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0905. Min Act: -0.0001

Data Index: 519363 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1330509 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1001. Min Act: -0.0001

Data Index: 572377 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1083549 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1193680 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0863. Min Act: -0.0001

Data Index: 785049 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0892. Min Act: -0.0001

Data Index: 19548 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0883. Min Act: -0.0001

Data Index: 3641 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0913. Min Act: -0.0001

Data Index: 506427 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1211681 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1174019 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0831. Min Act: -0.0001

Data Index: 27877 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.0831. Min Act: -0.0001

Data Index: 200179 (C4 (Web Text))

Max Activating Token Index: 75