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

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

Neuron 1678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.3504. Min Act: -0.0001

Data Index: 583263 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.3279. Min Act: -0.0000

Data Index: 358186 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.3463. Min Act: -0.0001

Data Index: 824604 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.3110. Min Act: -0.0001

Data Index: 749859 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2454. Min Act: -0.0001

Data Index: 973382 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2581. Min Act: -0.0000

Data Index: 136868 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2675. Min Act: -0.0001

Data Index: 306148 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2600. Min Act: -0.0001

Data Index: 711392 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2417. Min Act: -0.0001

Data Index: 629770 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2456. Min Act: -0.0000

Data Index: 252809 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2511. Min Act: -0.0000

Data Index: 133760 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2491. Min Act: -0.0000

Data Index: 724887 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2415. Min Act: -0.0001

Data Index: 280597 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2243. Min Act: -0.0001

Data Index: 99805 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2391. Min Act: -0.0001

Data Index: 357253 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1204482 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2177. Min Act: -0.0001

Data Index: 252446 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2292. Min Act: -0.0001

Data Index: 651653 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2467. Min Act: -0.0000

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.3504. Min Range: -0.3504

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1352228 (C4 (Web Text))

Max Activating Token Index: 237