Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 80 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.9221. Min Act: -0.0001

Data Index: 1274827 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.3509. Min Act: -0.0001

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.4528. Min Act: -0.0001

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.4583. Min Act: -0.0001

Data Index: 357583 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.4212. Min Act: -0.0001

Data Index: 119607 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.1816. Min Act: -0.0001

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.9797. Min Act: -0.0001

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.3625. Min Act: -0.0001

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.8737. Min Act: -0.0001

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.1494. Min Act: -0.0001

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.9884. Min Act: -0.0001

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.7781. Min Act: -0.0001

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.6350. Min Act: -0.0001

Data Index: 271178 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.9221. Min Range: -3.9221

Max Act: 3.1196. Min Act: -0.0001

Data Index: 99806 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.7983. Min Act: -0.0001

Data Index: 256758 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.6029. Min Act: -0.0001

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.7015. Min Act: -0.0001

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.8001. Min Act: -0.0001

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.3899. Min Act: -0.0001

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 3.9221. Min Range: -3.9221

Max Act: 2.6229. Min Act: -0.0001

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 219