Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.5136. Min Act: -0.0000

Data Index: 223478 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.4581. Min Act: -0.0000

Data Index: 776212 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.4498. Min Act: -0.0000

Data Index: 772835 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.2563. Min Act: -0.0000

Data Index: 71027 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1308160 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1164191 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.2336. Min Act: -0.0000

Data Index: 235368 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.1843. Min Act: -0.0000

Data Index: 836083 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1481992 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0678. Min Act: -0.0000

Data Index: 358224 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1070985 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1957986 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1844865 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0087. Min Act: 0.0000

Data Index: 1916693 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0685. Min Act: -0.0000

Data Index: 378004 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1406189 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1593008 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 1.5136. Min Range: -1.5136

Max Act: 0.9898. Min Act: -0.0000

Data Index: 942145 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.5136. Min Range: -1.5136

Max Act: 1.0556. Min Act: -0.0000

Data Index: 802846 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 1.5136. Min Range: -1.5136

Max Act: 0.9535. Min Act: -0.0000

Data Index: 261469 (The Pile)

Max Activating Token Index: 200