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

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

Neuron 912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5222. Min Act: -0.0001

Data Index: 759594 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5041. Min Act: -0.0001

Data Index: 1321704 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4589. Min Act: -0.0000

Data Index: 913122 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4697. Min Act: -0.0001

Data Index: 231205 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4743. Min Act: -0.0001

Data Index: 1578005 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4542. Min Act: -0.0001

Data Index: 1252385 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4380. Min Act: -0.0000

Data Index: 654464 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1042089 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4367. Min Act: -0.0001

Data Index: 536937 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4593. Min Act: -0.0000

Data Index: 811357 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4430. Min Act: -0.0001

Data Index: 159221 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4183. Min Act: -0.0001

Data Index: 563454 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4590. Min Act: -0.0001

Data Index: 734304 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3916. Min Act: -0.0000

Data Index: 962138 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4184. Min Act: -0.0000

Data Index: 524149 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4137. Min Act: -0.0001

Data Index: 451252 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3978. Min Act: -0.0001

Data Index: 144441 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1229965 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4029. Min Act: -0.0001

Data Index: 530755 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4032. Min Act: -0.0001

Data Index: 3050 (C4 (Web Text))

Max Activating Token Index: 749