Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3543. Min Act: -0.0001

Data Index: 926885 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1231815 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2918. Min Act: -0.0001

Data Index: 684510 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2523. Min Act: -0.0001

Data Index: 182633 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2466. Min Act: -0.0001

Data Index: 557677 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1270422 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2614. Min Act: -0.0001

Data Index: 825137 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2396. Min Act: -0.0001

Data Index: 728055 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2469. Min Act: -0.0001

Data Index: 803479 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2363. Min Act: -0.0001

Data Index: 1341126 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2427. Min Act: -0.0001

Data Index: 725338 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1023982 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2289. Min Act: -0.0001

Data Index: 1253061 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2186. Min Act: -0.0001

Data Index: 988048 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2227. Min Act: -0.0001

Data Index: 608225 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2234. Min Act: -0.0001

Data Index: 227129 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2208. Min Act: -0.0001

Data Index: 335109 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1186264 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2060. Min Act: -0.0001

Data Index: 626915 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.1984. Min Act: -0.0001

Data Index: 37846 (C4 (Web Text))

Max Activating Token Index: 305