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

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

Neuron 5090 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3571. Min Act: -0.0000

Data Index: 951137 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3497. Min Act: -0.0000

Data Index: 991379 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3255. Min Act: -0.0000

Data Index: 852913 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2954. Min Act: -0.0000

Data Index: 484333 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2644. Min Act: -0.0000

Data Index: 8978 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2784. Min Act: -0.0000

Data Index: 5166 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2656. Min Act: -0.0000

Data Index: 389571 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1268906 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2724. Min Act: -0.0000

Data Index: 454561 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2367. Min Act: -0.0000

Data Index: 47144 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2513. Min Act: -0.0000

Data Index: 953245 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2454. Min Act: -0.0000

Data Index: 982909 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1209898 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1309373 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2364. Min Act: -0.0000

Data Index: 959470 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1009216 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2329. Min Act: -0.0000

Data Index: 50519 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2127. Min Act: -0.0000

Data Index: 319444 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1182940 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2185. Min Act: -0.0000

Data Index: 873829 (C4 (Web Text))

Max Activating Token Index: 749