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

Dataset: The Pile

Neuron 1409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5951. Min Act: -0.0000

Data Index: 1555843 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1352835 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.6976. Min Act: -0.0000

Data Index: 1593885 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1805043 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.5740. Min Act: -0.0000

Data Index: 557527 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1265176 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1140502 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1813157 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3471. Min Act: -0.0000

Data Index: 632285 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3105. Min Act: -0.0000

Data Index: 414695 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1764302 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2915. Min Act: -0.0000

Data Index: 448631 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3244. Min Act: -0.0000

Data Index: 701165 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2113. Min Act: -0.0000

Data Index: 996683 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2281. Min Act: -0.0000

Data Index: 484841 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.3283. Min Act: -0.0000

Data Index: 974687 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2470. Min Act: -0.0000

Data Index: 1893528 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2236. Min Act: -0.0000

Data Index: 131560 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1249343 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 1.6976. Min Range: -1.6976

Max Act: 1.2328. Min Act: -0.0000

Data Index: 665275 (The Pile)

Max Activating Token Index: 594