Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2746 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0001

Data Index: 760133 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1144. Min Act: -0.0001

Data Index: 691401 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1116376 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1102. Min Act: -0.0001

Data Index: 945484 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1054. Min Act: -0.0001

Data Index: 323624 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1083. Min Act: -0.0001

Data Index: 239150 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0986. Min Act: -0.0001

Data Index: 654885 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0985. Min Act: -0.0001

Data Index: 614221 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0988. Min Act: -0.0001

Data Index: 147145 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1190097 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0949. Min Act: -0.0001

Data Index: 117507 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1330154 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0868. Min Act: -0.0001

Data Index: 779781 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1050703 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0900. Min Act: -0.0001

Data Index: 486352 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1250152 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0848. Min Act: -0.0001

Data Index: 212389 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0908. Min Act: -0.0001

Data Index: 287418 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0820. Min Act: -0.0001

Data Index: 285991 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0858. Min Act: -0.0001

Data Index: 276777 (C4 (Web Text))

Max Activating Token Index: 238