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

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

Neuron 3989 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: 0.2608. Min Range: -0.2608

Max Act: 0.2461. Min Act: -0.0000

Data Index: 57082 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2389. Min Act: -0.0000

Data Index: 97723 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2457. Min Act: -0.0000

Data Index: 183354 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2369. Min Act: -0.0000

Data Index: 290113 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1304981 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2476. Min Act: -0.0000

Data Index: 419593 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1222876 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1347423 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2422. Min Act: -0.0000

Data Index: 109065 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2534. Min Act: -0.0000

Data Index: 645652 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2380. Min Act: -0.0000

Data Index: 885792 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2188. Min Act: -0.0000

Data Index: 250212 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2442. Min Act: -0.0000

Data Index: 262192 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2315. Min Act: -0.0000

Data Index: 710558 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2411. Min Act: -0.0000

Data Index: 324988 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2395. Min Act: -0.0000

Data Index: 663836 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1340413 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2028. Min Act: -0.0000

Data Index: 941522 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2287. Min Act: -0.0000

Data Index: 671912 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1046124 (C4 (Web Text))

Max Activating Token Index: 802