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

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

Neuron 3210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8916. Min Act: -0.0001

Data Index: 284648 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8179. Min Act: -0.0001

Data Index: 470373 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1106540 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7756. Min Act: -0.0001

Data Index: 894996 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7414. Min Act: -0.0001

Data Index: 801570 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7499. Min Act: -0.0001

Data Index: 1289783 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6667. Min Act: -0.0001

Data Index: 731045 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7039. Min Act: -0.0001

Data Index: 237687 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6446. Min Act: -0.0001

Data Index: 1290493 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6349. Min Act: -0.0001

Data Index: 804234 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6628. Min Act: -0.0001

Data Index: 549807 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1100950 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5791. Min Act: -0.0001

Data Index: 926098 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1196748 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5832. Min Act: -0.0001

Data Index: 228050 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6196. Min Act: -0.0001

Data Index: 379834 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5883. Min Act: -0.0001

Data Index: 691153 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5874. Min Act: -0.0001

Data Index: 565074 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5573. Min Act: -0.0001

Data Index: 432546 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5931. Min Act: -0.0001

Data Index: 1130981 (C4 (Web Text))

Max Activating Token Index: 750