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

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

Neuron 2527 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5374. Min Act: -0.0003

Data Index: 1040045 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5526. Min Act: -0.0002

Data Index: 120983 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5062. Min Act: -0.0003

Data Index: 239472 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5022. Min Act: -0.0003

Data Index: 610212 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.5019. Min Act: -0.0003

Data Index: 612211 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4867. Min Act: -0.0003

Data Index: 1175323 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4785. Min Act: -0.0003

Data Index: 235334 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4613. Min Act: -0.0002

Data Index: 280411 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4605. Min Act: -0.0003

Data Index: 263901 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4445. Min Act: -0.0003

Data Index: 798511 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4438. Min Act: -0.0003

Data Index: 1126606 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4243. Min Act: -0.0003

Data Index: 782103 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4378. Min Act: -0.0003

Data Index: 368083 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4318. Min Act: -0.0003

Data Index: 1293398 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4316. Min Act: -0.0003

Data Index: 389012 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4193. Min Act: -0.0003

Data Index: 564659 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4148. Min Act: -0.0003

Data Index: 1105198 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4095. Min Act: -0.0003

Data Index: 645418 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4076. Min Act: -0.0003

Data Index: 370290 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.5526. Min Range: -0.5526

Max Act: 0.4075. Min Act: -0.0003

Data Index: 648736 (C4 (Web Text))

Max Activating Token Index: 672