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

Dataset: The Pile

Neuron 1091 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.4512. Min Act: -0.0000

Data Index: 249825 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1173961 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1771140 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1628. Min Act: -0.0000

Data Index: 796801 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0586. Min Act: -0.0000

Data Index: 162198 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1742. Min Act: -0.0000

Data Index: 321525 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1904. Min Act: -0.0000

Data Index: 403720 (The Pile)

Max Activating Token Index: 570

Text #7

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1857980 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0765. Min Act: -0.0000

Data Index: 684077 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1295100 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1376373 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0976. Min Act: -0.0000

Data Index: 379403 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1180605 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1090005 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0541. Min Act: -0.0000

Data Index: 618608 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1624479 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0169. Min Act: -0.0000

Data Index: 420533 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1234820 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1281374 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9472. Min Act: -0.0000

Data Index: 748398 (The Pile)

Max Activating Token Index: 105