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

Dataset: The Pile

Neuron 2461 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: 3.6762. Min Range: -3.6762

Max Act: 3.6326. Min Act: -0.0000

Data Index: 1176655 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 3.6762. Min Range: -3.6762

Max Act: 3.5505. Min Act: -0.0000

Data Index: 1056907 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 3.6762. Min Range: -3.6762

Max Act: 3.6762. Min Act: -0.0000

Data Index: 449759 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.5627. Min Act: -0.0000

Data Index: 96383 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 3.6762. Min Range: -3.6762

Max Act: 3.0598. Min Act: -0.0000

Data Index: 1436818 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1232180 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.6689. Min Act: -0.0000

Data Index: 1096513 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.7188. Min Act: -0.0000

Data Index: 700206 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.5568. Min Act: -0.0000

Data Index: 1944729 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.6934. Min Act: -0.0000

Data Index: 737940 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.7800. Min Act: -0.0000

Data Index: 1572772 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.3710. Min Act: -0.0000

Data Index: 576355 (The Pile)

Max Activating Token Index: 265

Text #12

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.4623. Min Act: -0.0000

Data Index: 1216428 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.4681. Min Act: -0.0000

Data Index: 1925300 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.4285. Min Act: -0.0000

Data Index: 1517670 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.3451. Min Act: -0.0000

Data Index: 561439 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.3228. Min Act: -0.0000

Data Index: 1353170 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.4450. Min Act: -0.0000

Data Index: 1717271 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.5172. Min Act: -0.0000

Data Index: 167541 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 3.6762. Min Range: -3.6762

Max Act: 2.5094. Min Act: -0.0000

Data Index: 939551 (The Pile)

Max Activating Token Index: 97