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

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

Neuron 3934 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.8989. Min Act: -0.0001

Data Index: 827794 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.8195. Min Act: -0.0002

Data Index: 1224694 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.8319. Min Act: -0.0001

Data Index: 804863 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7834. Min Act: -0.0001

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7797. Min Act: -0.0001

Data Index: 448019 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7492. Min Act: -0.0002

Data Index: 725634 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7443. Min Act: -0.0002

Data Index: 279193 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.6938. Min Act: -0.0002

Data Index: 458746 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7535. Min Act: -0.0002

Data Index: 430536 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.6890. Min Act: -0.0002

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7408. Min Act: -0.0002

Data Index: 1279332 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7273. Min Act: -0.0002

Data Index: 861440 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7191. Min Act: -0.0002

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.6704. Min Act: -0.0002

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7749. Min Act: -0.0002

Data Index: 634368 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7297. Min Act: -0.0001

Data Index: 112282 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7779. Min Act: -0.0001

Data Index: 366079 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7375. Min Act: -0.0002

Data Index: 458217 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7286. Min Act: -0.0002

Data Index: 589097 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.8989. Min Range: -0.8989

Max Act: 0.7340. Min Act: -0.0002

Data Index: 130459 (C4 (Web Text))

Max Activating Token Index: 79