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

Dataset: The Pile

Neuron 3267 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.4311. Min Act: -0.0000

Data Index: 722665 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2213. Min Act: -0.0000

Data Index: 764331 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1264163 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2418. Min Act: -0.0000

Data Index: 167286 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1717730 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0123. Min Act: -0.0000

Data Index: 55222 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1330067 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0837. Min Act: -0.0000

Data Index: 70610 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0100. Min Act: -0.0000

Data Index: 405561 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1724066 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9170. Min Act: -0.0000

Data Index: 805419 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1047624 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9505. Min Act: -0.0000

Data Index: 375162 (The Pile)

Max Activating Token Index: 292

Text #13

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1554124 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9532. Min Act: -0.0000

Data Index: 17925 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1442118 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9385. Min Act: -0.0000

Data Index: 847928 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1603714 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8782. Min Act: -0.0000

Data Index: 586655 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1508552 (The Pile)

Max Activating Token Index: 270