Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5066 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.9575. Min Act: -0.0000

Data Index: 392170 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1754183 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.8535. Min Act: -0.0000

Data Index: 779547 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1502148 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7971. Min Act: -0.0000

Data Index: 834454 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6991. Min Act: -0.0000

Data Index: 991212 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1646695 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1823149 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6377. Min Act: -0.0000

Data Index: 647014 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1449319 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1401710 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1642268 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1249228 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1000006 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6516. Min Act: -0.0000

Data Index: 398343 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1584533 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1749354 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1007670 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.5663. Min Act: -0.0000

Data Index: 997457 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.9575. Min Range: -0.9575

Max Act: 0.7071. Min Act: -0.0000

Data Index: 68759 (The Pile)

Max Activating Token Index: 623