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

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

Neuron 5560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1312669 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0735. Min Act: -0.0002

Data Index: 828681 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0714. Min Act: -0.0002

Data Index: 24411 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0735. Min Act: -0.0002

Data Index: 674519 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1014243 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0563. Min Act: -0.0002

Data Index: 229165 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0579. Min Act: -0.0002

Data Index: 362631 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0552. Min Act: -0.0002

Data Index: 901407 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0525. Min Act: -0.0002

Data Index: 977426 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0519. Min Act: -0.0002

Data Index: 213012 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1223069 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0514. Min Act: -0.0002

Data Index: 832191 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1155830 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0482. Min Act: -0.0002

Data Index: 345379 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1299530 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0448. Min Act: -0.0002

Data Index: 196622 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0442. Min Act: -0.0002

Data Index: 423476 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0452. Min Act: -0.0002

Data Index: 389390 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0442. Min Act: -0.0002

Data Index: 994764 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1109768 (C4 (Web Text))

Max Activating Token Index: 419