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

Dataset: The Pile

Neuron 573 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2269. Min Range: -1.2269

Max Act: 1.2269. Min Act: -0.0000

Data Index: 43400 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 1.2269. Min Range: -1.2269

Max Act: 1.0658. Min Act: -0.0000

Data Index: 311349 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 1.2269. Min Range: -1.2269

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1319682 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9950. Min Act: -0.0000

Data Index: 734463 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1173216 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9321. Min Act: -0.0000

Data Index: 108114 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1525621 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1267330 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8502. Min Act: -0.0000

Data Index: 90979 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1623763 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1605338 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8962. Min Act: 0.0000

Data Index: 1973898 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.9358. Min Act: -0.0000

Data Index: 520963 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1527480 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1646972 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8242. Min Act: -0.0000

Data Index: 206163 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1613233 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1611708 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1509571 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 1.2269. Min Range: -1.2269

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1259933 (The Pile)

Max Activating Token Index: 891