Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4254 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1082446 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2989. Min Act: -0.0000

Data Index: 31670 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.3209. Min Act: 0.0001

Data Index: 1338126 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2737. Min Act: -0.0000

Data Index: 867934 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2913. Min Act: -0.0000

Data Index: 313229 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2800. Min Act: -0.0000

Data Index: 338776 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1342487 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2763. Min Act: -0.0000

Data Index: 390308 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2614. Min Act: -0.0000

Data Index: 386220 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1243543 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2457. Min Act: -0.0000

Data Index: 306786 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2543. Min Act: -0.0000

Data Index: 216074 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2555. Min Act: -0.0000

Data Index: 356291 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2617. Min Act: -0.0000

Data Index: 847530 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1248247 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1060429 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2521. Min Act: -0.0000

Data Index: 282304 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2452. Min Act: -0.0000

Data Index: 503207 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1263089 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.4599. Min Range: -0.4599

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1058503 (C4 (Web Text))

Max Activating Token Index: 600