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

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

Neuron 3642 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.5126. Min Act: -0.0003

Data Index: 870879 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.5220. Min Act: -0.0003

Data Index: 1024474 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4908. Min Act: -0.0003

Data Index: 597870 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4273. Min Act: -0.0003

Data Index: 142585 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4181. Min Act: -0.0003

Data Index: 668036 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3980. Min Act: -0.0003

Data Index: 235970 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3886. Min Act: -0.0003

Data Index: 323492 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3857. Min Act: -0.0003

Data Index: 1244753 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3758. Min Act: -0.0003

Data Index: 115172 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3717. Min Act: -0.0003

Data Index: 279481 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3718. Min Act: -0.0003

Data Index: 1277021 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3310. Min Act: -0.0003

Data Index: 126341 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3530. Min Act: -0.0003

Data Index: 70013 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3490. Min Act: -0.0002

Data Index: 876341 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3454. Min Act: -0.0002

Data Index: 348498 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3426. Min Act: -0.0003

Data Index: 312116 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3130. Min Act: -0.0003

Data Index: 54015 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3045. Min Act: -0.0003

Data Index: 435046 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3011. Min Act: -0.0003

Data Index: 1055586 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2967. Min Act: -0.0003

Data Index: 630838 (C4 (Web Text))

Max Activating Token Index: 134