Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 247 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0001

Data Index: 155089 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1725. Min Act: -0.0001

Data Index: 641093 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1609. Min Act: -0.0001

Data Index: 467051 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1540. Min Act: -0.0001

Data Index: 609095 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1085731 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1250168 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1465. Min Act: -0.0001

Data Index: 845070 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1289688 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1276632 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1187232 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1391. Min Act: -0.0001

Data Index: 238947 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1289775 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1338. Min Act: -0.0001

Data Index: 366387 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1433. Min Act: -0.0001

Data Index: 998082 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1147621 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1354. Min Act: -0.0001

Data Index: 329607 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1298. Min Act: -0.0001

Data Index: 447021 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1216. Min Act: -0.0000

Data Index: 3078 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1321. Min Act: -0.0001

Data Index: 64385 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1280. Min Act: -0.0001

Data Index: 783716 (C4 (Web Text))

Max Activating Token Index: 879