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

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

Neuron 151 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.7323. Min Act: -0.0000

Data Index: 556990 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.5559. Min Act: -0.0000

Data Index: 95224 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.3114. Min Act: -0.0000

Data Index: 312077 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.2716. Min Act: -0.0000

Data Index: 747161 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.1244. Min Act: -0.0000

Data Index: 577307 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1089555 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1357418 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.1701. Min Act: -0.0000

Data Index: 45878 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.8512. Min Act: -0.0000

Data Index: 109682 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.7119. Min Act: -0.0000

Data Index: 446089 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.9251. Min Act: -0.0000

Data Index: 652720 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 2.7323. Min Range: -2.7323

Max Act: 2.0391. Min Act: -0.0000

Data Index: 836318 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.9962. Min Act: -0.0000

Data Index: 641315 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.7654. Min Act: -0.0000

Data Index: 22334 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.9135. Min Act: -0.0000

Data Index: 819494 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.6783. Min Act: -0.0000

Data Index: 136590 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1146713 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.7742. Min Act: -0.0000

Data Index: 816829 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.7162. Min Act: 0.0000

Data Index: 426561 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 2.7323. Min Range: -2.7323

Max Act: 1.6670. Min Act: -0.0000

Data Index: 190531 (C4 (Web Text))

Max Activating Token Index: 443