Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3156. Min Act: -0.0001

Data Index: 500132 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.3263. Min Act: -0.0000

Data Index: 410163 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2752. Min Act: -0.0000

Data Index: 230729 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2622. Min Act: -0.0000

Data Index: 804329 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2769. Min Act: -0.0000

Data Index: 227244 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2909. Min Act: -0.0000

Data Index: 655852 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2452. Min Act: -0.0001

Data Index: 123556 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2364. Min Act: -0.0000

Data Index: 51803 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2574. Min Act: -0.0001

Data Index: 26443 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2639. Min Act: -0.0001

Data Index: 630630 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1108781 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2470. Min Act: -0.0001

Data Index: 441981 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2358. Min Act: -0.0000

Data Index: 280030 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2477. Min Act: -0.0000

Data Index: 373622 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1098602 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1022674 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2247. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.3434. Min Range: -0.3434

Max Act: 0.2074. Min Act: -0.0001

Data Index: 260508 (C4 (Web Text))

Max Activating Token Index: 373