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

Dataset: The Pile

Neuron 1451 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1248485 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1406234 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1850742 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1155294 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5168. Min Act: -0.0000

Data Index: 824445 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5404. Min Act: -0.0000

Data Index: 384375 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5373. Min Act: -0.0000

Data Index: 105916 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1118248 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4832. Min Act: -0.0000

Data Index: 70913 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1514244 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4860. Min Act: -0.0000

Data Index: 714797 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4971. Min Act: -0.0000

Data Index: 2720 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5091. Min Act: -0.0000

Data Index: 474906 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1433762 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4968. Min Act: -0.0000

Data Index: 329858 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5015. Min Act: -0.0000

Data Index: 957214 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1323618 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.5167. Min Act: -0.0000

Data Index: 722441 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1641341 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 0.5705. Min Range: -0.5705

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1183195 (The Pile)

Max Activating Token Index: 872