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

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

Neuron 3093 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: 0.3443. Min Range: -0.3443

Max Act: 0.3443. Min Act: -0.0000

Data Index: 112109 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1015650 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.3297. Min Act: -0.0000

Data Index: 526663 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.3313. Min Act: -0.0000

Data Index: 702181 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.3370. Min Act: -0.0000

Data Index: 84513 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2828. Min Act: -0.0000

Data Index: 420990 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2932. Min Act: -0.0000

Data Index: 650885 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1177381 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2962. Min Act: -0.0000

Data Index: 654728 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2713. Min Act: 0.0000

Data Index: 145457 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1277051 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2583. Min Act: -0.0000

Data Index: 507081 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1289536 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1090619 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2685. Min Act: -0.0000

Data Index: 698530 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2444. Min Act: -0.0000

Data Index: 310475 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2529. Min Act: -0.0000

Data Index: 457505 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2396. Min Act: -0.0000

Data Index: 482937 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1233329 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.3443. Min Range: -0.3443

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1213843 (C4 (Web Text))

Max Activating Token Index: 134