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

Dataset: The Pile

Neuron 2170 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: 0.9215. Min Range: -0.9215

Max Act: 0.9215. Min Act: -0.0000

Data Index: 71579 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1818786 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7593. Min Act: -0.0000

Data Index: 157808 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1872940 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1444510 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1965622 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1224365 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1806566 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1688112 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5764. Min Act: -0.0000

Data Index: 929637 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1950889 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1531118 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5897. Min Act: -0.0000

Data Index: 247717 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5532. Min Act: -0.0000

Data Index: 71355 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5645. Min Act: -0.0000

Data Index: 487993 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1154967 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5338. Min Act: -0.0000

Data Index: 412816 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1400435 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1903049 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1234904 (The Pile)

Max Activating Token Index: 562