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

Dataset: The Pile

Neuron 566 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: 1.1986. Min Range: -1.1986

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1363602 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1427. Min Act: -0.0000

Data Index: 966738 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1145. Min Act: -0.0000

Data Index: 149086 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0905. Min Act: -0.0000

Data Index: 364448 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0968. Min Act: -0.0000

Data Index: 957718 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0195. Min Act: -0.0000

Data Index: 298730 (The Pile)

Max Activating Token Index: 631

Text #6

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1401150 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0680. Min Act: -0.0000

Data Index: 936015 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0630. Min Act: -0.0000

Data Index: 308374 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0554. Min Act: -0.0000

Data Index: 781583 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1431648 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9637. Min Act: -0.0000

Data Index: 956737 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0257. Min Act: -0.0000

Data Index: 342142 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1287024 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1084. Min Act: -0.0000

Data Index: 704557 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1976182 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1695040 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9840. Min Act: -0.0000

Data Index: 692610 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1977497 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0262. Min Act: -0.0000

Data Index: 804343 (The Pile)

Max Activating Token Index: 440