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

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

Neuron 3472 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: 0.4484. Min Range: -0.4484

Max Act: 0.4484. Min Act: -0.0001

Data Index: 400636 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4029. Min Act: -0.0001

Data Index: 844176 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3582. Min Act: -0.0001

Data Index: 1289056 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1004105 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3433. Min Act: -0.0001

Data Index: 80682 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3129. Min Act: -0.0001

Data Index: 1180119 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3314. Min Act: -0.0001

Data Index: 656486 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3351. Min Act: -0.0001

Data Index: 853502 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3250. Min Act: -0.0001

Data Index: 288460 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1292499 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3066. Min Act: -0.0001

Data Index: 1060477 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3193. Min Act: -0.0001

Data Index: 631558 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2868. Min Act: -0.0001

Data Index: 40723 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3274. Min Act: -0.0001

Data Index: 4621 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1080852 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2808. Min Act: -0.0001

Data Index: 848421 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2784. Min Act: -0.0001

Data Index: 815550 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3207. Min Act: -0.0001

Data Index: 249910 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1036307 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1356309 (C4 (Web Text))

Max Activating Token Index: 497