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

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

Neuron 4080 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0001

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8591. Min Act: -0.0001

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8038. Min Act: -0.0001

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7623. Min Act: -0.0001

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7758. Min Act: -0.0001

Data Index: 736016 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7110. Min Act: -0.0001

Data Index: 155790 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7691. Min Act: -0.0001

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7223. Min Act: -0.0001

Data Index: 558573 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6852. Min Act: -0.0001

Data Index: 470097 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6246. Min Act: -0.0001

Data Index: 596198 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1258264 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5949. Min Act: -0.0001

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6686. Min Act: -0.0001

Data Index: 96919 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5744. Min Act: -0.0001

Data Index: 69847 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5910. Min Act: -0.0001

Data Index: 241953 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6059. Min Act: -0.0001

Data Index: 1203789 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5926. Min Act: -0.0001

Data Index: 380518 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5554. Min Act: -0.0001

Data Index: 521612 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1183274 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5432. Min Act: -0.0001

Data Index: 721260 (C4 (Web Text))

Max Activating Token Index: 873