Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2319. Min Range: -1.2319

Max Act: 1.2319. Min Act: -0.0000

Data Index: 1095469 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1589388 (The Pile)

Max Activating Token Index: 417

Text #2

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9764. Min Act: -0.0000

Data Index: 402146 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1450360 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8718. Min Act: -0.0000

Data Index: 926607 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7682. Min Act: -0.0000

Data Index: 765940 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1165391 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1532863 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1521819 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8397. Min Act: -0.0000

Data Index: 414234 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7601. Min Act: -0.0000

Data Index: 165338 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8040. Min Act: -0.0000

Data Index: 682536 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1733928 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1659037 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.8001. Min Act: -0.0000

Data Index: 310597 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1433800 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1485511 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7970. Min Act: -0.0000

Data Index: 167066 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7867. Min Act: -0.0000

Data Index: 984442 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 1.2319. Min Range: -1.2319

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1248431 (The Pile)

Max Activating Token Index: 153