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

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

Neuron 396 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: 0.5358. Min Range: -0.5358

Max Act: 0.4954. Min Act: -0.0001

Data Index: 323341 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5065. Min Act: -0.0002

Data Index: 1019681 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5290. Min Act: -0.0001

Data Index: 636997 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4893. Min Act: -0.0001

Data Index: 469627 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1138434 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4943. Min Act: -0.0001

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4477. Min Act: -0.0001

Data Index: 929146 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4745. Min Act: -0.0001

Data Index: 380238 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4587. Min Act: -0.0001

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4525. Min Act: -0.0001

Data Index: 798928 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4670. Min Act: -0.0001

Data Index: 920979 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5004. Min Act: -0.0001

Data Index: 939884 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4081. Min Act: -0.0001

Data Index: 420820 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4411. Min Act: -0.0001

Data Index: 58937 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4759. Min Act: -0.0002

Data Index: 82922 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1277237 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4177. Min Act: -0.0002

Data Index: 1223130 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4283. Min Act: -0.0001

Data Index: 1202033 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4134. Min Act: -0.0001

Data Index: 1092647 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3931. Min Act: -0.0001

Data Index: 567231 (C4 (Web Text))

Max Activating Token Index: 318