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

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

Neuron 3213 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3358. Min Range: -3.3358

Max Act: 3.3358. Min Act: -0.0000

Data Index: 957636 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 3.3358. Min Range: -3.3358

Max Act: 3.3215. Min Act: -0.0000

Data Index: 948233 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.7746. Min Act: -0.0000

Data Index: 989219 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.3358. Min Range: -3.3358

Max Act: 3.1459. Min Act: -0.0000

Data Index: 1180826 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.8504. Min Act: -0.0000

Data Index: 1009901 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.3358. Min Range: -3.3358

Max Act: 3.1253. Min Act: -0.0000

Data Index: 611101 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.9657. Min Act: -0.0000

Data Index: 932930 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.8984. Min Act: -0.0000

Data Index: 1053267 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.8995. Min Act: -0.0000

Data Index: 920887 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.9532. Min Act: -0.0000

Data Index: 1333141 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.8898. Min Act: -0.0000

Data Index: 173169 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.6113. Min Act: -0.0000

Data Index: 995489 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.7039. Min Act: -0.0000

Data Index: 1108974 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.7898. Min Act: -0.0000

Data Index: 965086 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.3996. Min Act: -0.0000

Data Index: 925737 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.6397. Min Act: -0.0000

Data Index: 931998 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.6425. Min Act: -0.0000

Data Index: 906371 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.6258. Min Act: -0.0000

Data Index: 292464 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.7459. Min Act: -0.0000

Data Index: 471931 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.3358. Min Range: -3.3358

Max Act: 2.6094. Min Act: -0.0000

Data Index: 867305 (C4 (Web Text))

Max Activating Token Index: 748