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

Dataset: The Pile

Neuron 3181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.4337. Min Act: -0.0000

Data Index: 739898 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1375620 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0836. Min Act: -0.0000

Data Index: 406635 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1974293 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0563. Min Act: -0.0000

Data Index: 121945 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1620745 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1125307 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2787. Min Act: -0.0000

Data Index: 298705 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.4337. Min Range: -1.4337

Max Act: 0.9889. Min Act: -0.0000

Data Index: 877821 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2032. Min Act: -0.0000

Data Index: 676852 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1501328 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1391. Min Act: -0.0000

Data Index: 168940 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1403421 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1307723 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0472. Min Act: -0.0000

Data Index: 670236 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1021565 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1912623 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1412788 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 1.4337. Min Range: -1.4337

Max Act: 0.9614. Min Act: -0.0000

Data Index: 611568 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 1.4337. Min Range: -1.4337

Max Act: 1.0573. Min Act: -0.0000

Data Index: 276452 (The Pile)

Max Activating Token Index: 988