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

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

Neuron 4644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.6158. Min Act: -0.0000

Data Index: 860173 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.5691. Min Act: -0.0000

Data Index: 124658 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1239397 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.6166. Min Act: -0.0000

Data Index: 456325 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4806. Min Act: -0.0000

Data Index: 604973 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.3297. Min Act: -0.0001

Data Index: 41260 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4559. Min Act: -0.0000

Data Index: 1205133 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4014. Min Act: -0.0000

Data Index: 139238 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4918. Min Act: -0.0000

Data Index: 121377 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4093. Min Act: -0.0000

Data Index: 600027 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.3126. Min Act: -0.0000

Data Index: 731483 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.3428. Min Act: -0.0000

Data Index: 851326 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.3403. Min Act: -0.0000

Data Index: 267307 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.2514. Min Act: -0.0000

Data Index: 852263 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4304. Min Act: -0.0000

Data Index: 812512 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.3931. Min Act: -0.0000

Data Index: 47919 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.3234. Min Act: -0.0000

Data Index: 449035 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1196859 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.2193. Min Act: -0.0000

Data Index: 223566 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.6380. Min Range: -1.6380

Max Act: 1.4384. Min Act: -0.0000

Data Index: 170469 (C4 (Web Text))

Max Activating Token Index: 621