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

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

Neuron 2723 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2483. Min Act: -0.0000

Data Index: 365176 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1348193 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2565. Min Act: -0.0000

Data Index: 459508 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2715. Min Act: -0.0000

Data Index: 945030 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2433. Min Act: -0.0000

Data Index: 160391 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2400. Min Act: -0.0000

Data Index: 289710 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2355. Min Act: -0.0000

Data Index: 544216 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2523. Min Act: -0.0000

Data Index: 118441 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2415. Min Act: -0.0000

Data Index: 330099 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2411. Min Act: -0.0000

Data Index: 794644 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2376. Min Act: -0.0000

Data Index: 584300 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2178. Min Act: -0.0000

Data Index: 984186 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1006023 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2394. Min Act: -0.0000

Data Index: 373071 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2168. Min Act: -0.0000

Data Index: 104826 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1136176 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2365. Min Act: -0.0000

Data Index: 417948 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2265. Min Act: -0.0000

Data Index: 475936 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1318888 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2256. Min Act: -0.0000

Data Index: 467323 (C4 (Web Text))

Max Activating Token Index: 688