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

Dataset: The Pile

Neuron 2816 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: 0.1683. Min Range: -0.1683

Max Act: 0.1513. Min Act: -0.0000

Data Index: 89514 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1683. Min Act: -0.0000

Data Index: 801066 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1189433 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1488. Min Act: -0.0000

Data Index: 949219 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1315. Min Act: -0.0000

Data Index: 982977 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1227. Min Act: -0.0000

Data Index: 159571 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1298162 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1129. Min Act: -0.0000

Data Index: 845449 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1065. Min Act: -0.0000

Data Index: 259614 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1491037 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1509140 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1926420 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1029. Min Act: -0.0000

Data Index: 375925 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.0975. Min Act: 0.0000

Data Index: 1153427 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.0967. Min Act: -0.0000

Data Index: 66688 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1155. Min Act: -0.0000

Data Index: 219955 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1010314 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.0997. Min Act: -0.0000

Data Index: 918873 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.0919. Min Act: -0.0000

Data Index: 457661 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.1683. Min Range: -0.1683

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1982060 (The Pile)

Max Activating Token Index: 863