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

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

Neuron 2108 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4309. Min Act: -0.0000

Data Index: 790333 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3260. Min Act: -0.0000

Data Index: 510316 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3042. Min Act: -0.0000

Data Index: 409548 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3122. Min Act: -0.0000

Data Index: 214135 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1265094 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2954. Min Act: -0.0000

Data Index: 213510 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1215535 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2915. Min Act: -0.0000

Data Index: 210540 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1058500 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2691. Min Act: -0.0000

Data Index: 31435 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2676. Min Act: -0.0000

Data Index: 145913 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2636. Min Act: -0.0000

Data Index: 551946 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2568. Min Act: -0.0000

Data Index: 940443 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2780. Min Act: -0.0000

Data Index: 921509 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2509. Min Act: -0.0000

Data Index: 727942 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2606. Min Act: -0.0000

Data Index: 122452 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2564. Min Act: -0.0000

Data Index: 304408 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2618. Min Act: -0.0000

Data Index: 945322 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2515. Min Act: -0.0000

Data Index: 596985 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1040226 (C4 (Web Text))

Max Activating Token Index: 213