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

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

Neuron 3128 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1034509 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.7149. Min Act: -0.0001

Data Index: 321132 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6183. Min Act: -0.0001

Data Index: 562756 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6158. Min Act: -0.0001

Data Index: 320279 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6084. Min Act: -0.0001

Data Index: 154584 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1196340 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5949. Min Act: -0.0001

Data Index: 817168 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5361. Min Act: -0.0001

Data Index: 730751 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5544. Min Act: -0.0001

Data Index: 580182 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1353952 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5199. Min Act: -0.0001

Data Index: 113442 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5381. Min Act: -0.0001

Data Index: 522453 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5332. Min Act: -0.0001

Data Index: 421142 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1462697 (Python Code)

Max Activating Token Index: 750

Text #14

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5224. Min Act: -0.0001

Data Index: 585320 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5043. Min Act: -0.0001

Data Index: 903258 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5478. Min Act: -0.0001

Data Index: 718633 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5178. Min Act: -0.0001

Data Index: 28386 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1156101 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5141. Min Act: -0.0001

Data Index: 10757 (C4 (Web Text))

Max Activating Token Index: 448