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

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

Neuron 2797 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.5159. Min Act: -0.0000

Data Index: 181359 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.5627. Min Act: -0.0000

Data Index: 104961 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4661. Min Act: -0.0000

Data Index: 988981 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4782. Min Act: -0.0000

Data Index: 541836 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4772. Min Act: -0.0000

Data Index: 690422 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.3998. Min Act: -0.0000

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4151. Min Act: -0.0000

Data Index: 736728 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4542. Min Act: -0.0000

Data Index: 598531 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4204. Min Act: -0.0000

Data Index: 93542 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4040. Min Act: -0.0000

Data Index: 466901 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.3918. Min Act: -0.0000

Data Index: 654312 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4255. Min Act: -0.0000

Data Index: 188733 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4283. Min Act: -0.0000

Data Index: 186028 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1283339 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4339. Min Act: -0.0000

Data Index: 150226 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.3847. Min Act: -0.0000

Data Index: 145644 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4741. Min Act: -0.0000

Data Index: 654223 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4078. Min Act: -0.0000

Data Index: 488356 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4087. Min Act: -0.0000

Data Index: 28776 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.5627. Min Range: -0.5627

Max Act: 0.4206. Min Act: -0.0000

Data Index: 448293 (C4 (Web Text))

Max Activating Token Index: 657