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

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

Neuron 1876 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0918. Min Range: -1.0918

Max Act: 1.0160. Min Act: -0.0001

Data Index: 1189449 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 1.0918. Min Range: -1.0918

Max Act: 1.0918. Min Act: -0.0001

Data Index: 545582 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.0918. Min Range: -1.0918

Max Act: 1.0382. Min Act: -0.0001

Data Index: 1227921 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 1.0918. Min Range: -1.0918

Max Act: 1.0016. Min Act: -0.0001

Data Index: 62007 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9899. Min Act: -0.0001

Data Index: 1076743 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1267796 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9847. Min Act: -0.0001

Data Index: 196316 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9852. Min Act: -0.0001

Data Index: 477388 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9238. Min Act: -0.0001

Data Index: 871991 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1126586 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.0918. Min Range: -1.0918

Max Act: 1.0208. Min Act: -0.0001

Data Index: 12470 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9153. Min Act: -0.0001

Data Index: 954038 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9372. Min Act: -0.0001

Data Index: 8452 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8845. Min Act: -0.0001

Data Index: 351433 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8550. Min Act: -0.0001

Data Index: 525757 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8963. Min Act: -0.0001

Data Index: 277512 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8650. Min Act: -0.0001

Data Index: 289820 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8584. Min Act: -0.0001

Data Index: 796325 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8252. Min Act: -0.0001

Data Index: 1015731 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8173. Min Act: -0.0001

Data Index: 7611 (C4 (Web Text))

Max Activating Token Index: 279