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

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

Neuron 3555 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: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0000

Data Index: 917768 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2827. Min Act: -0.0000

Data Index: 942956 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2736. Min Act: -0.0000

Data Index: 649849 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2702. Min Act: -0.0000

Data Index: 41584 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2693. Min Act: -0.0000

Data Index: 910311 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2650. Min Act: -0.0000

Data Index: 679389 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1074754 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1193084 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2380. Min Act: -0.0000

Data Index: 955857 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2317. Min Act: -0.0001

Data Index: 1273352 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1278724 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2247. Min Act: -0.0000

Data Index: 812383 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2426. Min Act: -0.0000

Data Index: 91429 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1141982 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1134984 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2077. Min Act: -0.0000

Data Index: 234139 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1141185 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1144372 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1094467 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2119. Min Act: -0.0001

Data Index: 942551 (C4 (Web Text))

Max Activating Token Index: 176