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

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

Neuron 3248 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2643. Min Act: -0.0003

Data Index: 859329 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2909. Min Act: -0.0003

Data Index: 210402 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2647. Min Act: -0.0003

Data Index: 1171810 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2678. Min Act: -0.0003

Data Index: 82752 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2455. Min Act: -0.0003

Data Index: 1146140 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2543. Min Act: -0.0003

Data Index: 885208 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2557. Min Act: -0.0003

Data Index: 47519 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2647. Min Act: -0.0003

Data Index: 1131008 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2533. Min Act: -0.0003

Data Index: 865540 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2755. Min Act: -0.0003

Data Index: 1025842 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2385. Min Act: -0.0003

Data Index: 983426 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2514. Min Act: -0.0003

Data Index: 1208434 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2418. Min Act: -0.0003

Data Index: 1178394 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.3583. Min Act: -0.0003

Data Index: 770716 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2405. Min Act: -0.0003

Data Index: 68457 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2248. Min Act: -0.0003

Data Index: 475227 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2200. Min Act: -0.0003

Data Index: 928375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2537. Min Act: -0.0003

Data Index: 349632 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.1966. Min Act: -0.0003

Data Index: 317137 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2596. Min Act: -0.0003

Data Index: 726504 (C4 (Web Text))

Max Activating Token Index: 67