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

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

Neuron 58 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2355. Min Act: -0.0000

Data Index: 876387 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2417. Min Act: -0.0000

Data Index: 959396 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1126061 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2552. Min Act: -0.0000

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2430. Min Act: -0.0000

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2378. Min Act: -0.0000

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2237. Min Act: -0.0000

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2356. Min Act: -0.0000

Data Index: 542350 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2094. Min Act: -0.0000

Data Index: 317104 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1301738 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2289. Min Act: -0.0000

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2405. Min Act: -0.0000

Data Index: 793114 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2290. Min Act: -0.0000

Data Index: 286191 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1981. Min Act: -0.0000

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2275. Min Act: -0.0000

Data Index: 717716 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2094. Min Act: -0.0000

Data Index: 876732 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2099. Min Act: -0.0000

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1134817 (C4 (Web Text))

Max Activating Token Index: 932