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

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

Neuron 2810 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: 1.5156. Min Range: -1.5156

Max Act: 1.5156. Min Act: -0.0000

Data Index: 193983 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1231643 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.4001. Min Act: -0.0000

Data Index: 344216 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.4255. Min Act: -0.0000

Data Index: 514784 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.4664. Min Act: -0.0000

Data Index: 995333 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1004897 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.4355. Min Act: -0.0000

Data Index: 770996 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1919. Min Act: -0.0000

Data Index: 865027 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1141352 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.3856. Min Act: -0.0000

Data Index: 545262 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.3243. Min Act: -0.0000

Data Index: 112929 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2093. Min Act: -0.0000

Data Index: 268563 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2735. Min Act: -0.0000

Data Index: 899253 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2983. Min Act: -0.0000

Data Index: 445945 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2939. Min Act: -0.0000

Data Index: 792103 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1878. Min Act: -0.0000

Data Index: 25369 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1127704 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1758. Min Act: -0.0000

Data Index: 135282 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1223429 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 1.5156. Min Range: -1.5156

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1307577 (C4 (Web Text))

Max Activating Token Index: 627