Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 760 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0428. Min Act: -0.0001

Data Index: 830112 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0836. Min Act: -0.0001

Data Index: 373508 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0313. Min Act: -0.0001

Data Index: 367899 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8302. Min Act: -0.0001

Data Index: 227727 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0644. Min Act: -0.0001

Data Index: 850281 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9852. Min Act: -0.0001

Data Index: 804350 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8502. Min Act: -0.0001

Data Index: 324697 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8938. Min Act: -0.0001

Data Index: 785344 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9213. Min Act: -0.0001

Data Index: 1185065 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9386. Min Act: -0.0001

Data Index: 980581 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8914. Min Act: -0.0001

Data Index: 138610 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9124. Min Act: -0.0001

Data Index: 538835 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8606. Min Act: -0.0001

Data Index: 207529 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9297. Min Act: -0.0001

Data Index: 842403 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1104742 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8743. Min Act: -0.0001

Data Index: 1064593 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8472. Min Act: -0.0001

Data Index: 745731 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8612. Min Act: -0.0001

Data Index: 703311 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8762. Min Act: -0.0001

Data Index: 339221 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7999. Min Act: -0.0001

Data Index: 118047 (C4 (Web Text))

Max Activating Token Index: 36