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

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

Neuron 4753 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.8216. Min Act: -0.0001

Data Index: 683127 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7685. Min Act: -0.0001

Data Index: 965323 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7417. Min Act: -0.0001

Data Index: 1358723 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7105. Min Act: -0.0001

Data Index: 649902 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6724. Min Act: -0.0001

Data Index: 1310092 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6412. Min Act: -0.0001

Data Index: 79947 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5351. Min Act: -0.0001

Data Index: 1233005 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5802. Min Act: -0.0001

Data Index: 1095364 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5571. Min Act: -0.0001

Data Index: 714227 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6772. Min Act: -0.0001

Data Index: 247794 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5767. Min Act: -0.0001

Data Index: 98953 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5620. Min Act: -0.0001

Data Index: 599567 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5411. Min Act: -0.0001

Data Index: 591833 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5342. Min Act: -0.0001

Data Index: 1014351 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5259. Min Act: -0.0001

Data Index: 1120967 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5184. Min Act: -0.0001

Data Index: 1357083 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.5319. Min Act: -0.0001

Data Index: 846568 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.4903. Min Act: -0.0001

Data Index: 501978 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.4549. Min Act: -0.0001

Data Index: 1021307 (C4 (Web Text))

Max Activating Token Index: 329