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

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

Neuron 94 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1086215 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.2280. Min Act: -0.0000

Data Index: 275662 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.1007. Min Act: -0.0001

Data Index: 322214 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1043984 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0740. Min Act: -0.0000

Data Index: 519990 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1156921 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1627434 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9588. Min Act: -0.0001

Data Index: 1005848 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9535. Min Act: -0.0001

Data Index: 933794 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1082858 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1130751 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.9479. Min Act: -0.0000

Data Index: 188469 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.2280. Min Range: -1.2280

Max Act: 1.0725. Min Act: -0.0000

Data Index: 906500 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1303457 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8882. Min Act: -0.0000

Data Index: 188417 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8214. Min Act: -0.0000

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8804. Min Act: -0.0000

Data Index: 39295 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8762. Min Act: -0.0000

Data Index: 753295 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8410. Min Act: -0.0000

Data Index: 284602 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 1.2280. Min Range: -1.2280

Max Act: 0.8750. Min Act: -0.0000

Data Index: 671311 (C4 (Web Text))

Max Activating Token Index: 847