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

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

Neuron 475 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.3190. Min Act: -0.0000

Data Index: 873319 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2930. Min Act: -0.0000

Data Index: 619638 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2892. Min Act: -0.0000

Data Index: 203371 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2906. Min Act: -0.0000

Data Index: 921427 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2693. Min Act: -0.0000

Data Index: 587769 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2702. Min Act: -0.0000

Data Index: 965757 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1035539 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2666. Min Act: -0.0000

Data Index: 813800 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2568. Min Act: -0.0000

Data Index: 534266 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1277931 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2649. Min Act: -0.0000

Data Index: 630464 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2633. Min Act: -0.0000

Data Index: 496669 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1062741 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2602. Min Act: -0.0000

Data Index: 763767 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1400605 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2454. Min Act: -0.0000

Data Index: 767016 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1287478 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2361. Min Act: -0.0000

Data Index: 864531 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1418508 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 0.3190. Min Range: -0.3190

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1079712 (C4 (Web Text))

Max Activating Token Index: 133