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

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

Neuron 3770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5735. Min Act: -0.0001

Data Index: 670656 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4892. Min Act: -0.0000

Data Index: 907199 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5292. Min Act: -0.0001

Data Index: 1288004 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5363. Min Act: -0.0001

Data Index: 37719 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5024. Min Act: -0.0001

Data Index: 108764 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4286. Min Act: -0.0001

Data Index: 178919 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1190392 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4836. Min Act: -0.0001

Data Index: 620319 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4094. Min Act: -0.0000

Data Index: 836331 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1225441 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4528. Min Act: -0.0001

Data Index: 656458 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1207251 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4184. Min Act: -0.0000

Data Index: 139233 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4329. Min Act: -0.0001

Data Index: 738231 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1269534 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4009. Min Act: -0.0000

Data Index: 578377 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4754. Min Act: -0.0001

Data Index: 981592 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4488. Min Act: -0.0001

Data Index: 42261 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4106. Min Act: -0.0001

Data Index: 136983 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.5735. Min Range: -0.5735

Max Act: 0.4126. Min Act: -0.0001

Data Index: 365519 (C4 (Web Text))

Max Activating Token Index: 317