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

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

Neuron 3727 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.7176. Min Act: -0.0001

Data Index: 949509 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.7400. Min Act: -0.0001

Data Index: 596386 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.7184. Min Act: -0.0001

Data Index: 935676 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6448. Min Act: -0.0001

Data Index: 30312 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6319. Min Act: -0.0001

Data Index: 665542 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1328825 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6629. Min Act: -0.0001

Data Index: 607038 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.7019. Min Act: -0.0001

Data Index: 1172536 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6798. Min Act: -0.0001

Data Index: 955624 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1000784 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6141. Min Act: -0.0001

Data Index: 763528 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6333. Min Act: -0.0001

Data Index: 783480 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6380. Min Act: -0.0001

Data Index: 563130 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6197. Min Act: -0.0001

Data Index: 1024513 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1019133 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.5917. Min Act: -0.0001

Data Index: 738512 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1102977 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.5662. Min Act: -0.0001

Data Index: 208549 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.5882. Min Act: -0.0001

Data Index: 1244308 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.7400. Min Range: -0.7400

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1216648 (C4 (Web Text))

Max Activating Token Index: 28