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

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

Neuron 1390 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1073934 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5063. Min Act: -0.0000

Data Index: 659312 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1290132 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4754. Min Act: -0.0000

Data Index: 850749 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1198613 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4936. Min Act: -0.0000

Data Index: 129943 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4579. Min Act: -0.0000

Data Index: 370760 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4603. Min Act: -0.0000

Data Index: 399932 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4757. Min Act: -0.0000

Data Index: 630278 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4901. Min Act: -0.0000

Data Index: 453144 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4780. Min Act: -0.0000

Data Index: 616073 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4595. Min Act: -0.0000

Data Index: 313247 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4546. Min Act: -0.0000

Data Index: 62457 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4701. Min Act: -0.0000

Data Index: 822998 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4696. Min Act: -0.0000

Data Index: 424892 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4509. Min Act: -0.0000

Data Index: 992290 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4302. Min Act: -0.0000

Data Index: 523997 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1021963 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4234. Min Act: -0.0000

Data Index: 619921 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.9238. Min Range: -0.9238

Max Act: 0.4214. Min Act: -0.0000

Data Index: 698697 (C4 (Web Text))

Max Activating Token Index: 872