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

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

Neuron 3061 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0207. Min Range: -1.0207

Max Act: 1.0207. Min Act: -0.0001

Data Index: 228428 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7751. Min Act: -0.0002

Data Index: 1186850 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.7088. Min Act: -0.0001

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1119005 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5991. Min Act: -0.0001

Data Index: 569627 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.6211. Min Act: -0.0001

Data Index: 968422 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5994. Min Act: -0.0002

Data Index: 1024386 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5300. Min Act: -0.0001

Data Index: 1342353 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5812. Min Act: -0.0001

Data Index: 718417 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5034. Min Act: -0.0001

Data Index: 908440 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5477. Min Act: -0.0001

Data Index: 97089 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5227. Min Act: -0.0001

Data Index: 568171 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5071. Min Act: -0.0001

Data Index: 1155914 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.4594. Min Act: -0.0001

Data Index: 782958 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.4514. Min Act: -0.0001

Data Index: 841015 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.4864. Min Act: -0.0002

Data Index: 794794 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.4775. Min Act: -0.0001

Data Index: 1289818 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5230. Min Act: -0.0001

Data Index: 64494 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1165836 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.0207. Min Range: -1.0207

Max Act: 0.5474. Min Act: -0.0001

Data Index: 47848 (C4 (Web Text))

Max Activating Token Index: 941