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

Dataset: The Pile

Neuron 3020 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: 0.9299. Min Range: -0.9299

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1637954 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.9171. Min Act: -0.0000

Data Index: 700265 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1579710 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7924. Min Act: -0.0000

Data Index: 621321 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1400234 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6591. Min Act: -0.0000

Data Index: 538417 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7299. Min Act: -0.0000

Data Index: 555541 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1356734 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1619454 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7608. Min Act: 0.0000

Data Index: 1123915 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1930588 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7781. Min Act: -0.0000

Data Index: 395350 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7097. Min Act: -0.0000

Data Index: 316784 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1348396 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.7405. Min Act: -0.0000

Data Index: 106998 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6652. Min Act: -0.0000

Data Index: 456113 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6683. Min Act: 0.0000

Data Index: 1302034 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1482129 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1304342 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.9299. Min Range: -0.9299

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1992084 (The Pile)

Max Activating Token Index: 91