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

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

Neuron 3092 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: 0.7880. Min Range: -0.7880

Max Act: 0.7880. Min Act: -0.0000

Data Index: 864716 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6020. Min Act: -0.0000

Data Index: 19061 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5664. Min Act: -0.0000

Data Index: 468535 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5138. Min Act: -0.0000

Data Index: 24137 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5202. Min Act: -0.0000

Data Index: 544968 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4889. Min Act: -0.0000

Data Index: 176640 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1083921 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4429. Min Act: -0.0000

Data Index: 900660 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1263222 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4335. Min Act: -0.0000

Data Index: 607189 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4216. Min Act: -0.0000

Data Index: 31178 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1210874 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4514. Min Act: -0.0000

Data Index: 987054 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1294869 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4660. Min Act: -0.0000

Data Index: 833282 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4118. Min Act: -0.0000

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4241. Min Act: -0.0000

Data Index: 208467 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4200. Min Act: -0.0000

Data Index: 325880 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1233725 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.4069. Min Act: -0.0000

Data Index: 849692 (C4 (Web Text))

Max Activating Token Index: 680