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

Dataset: The Pile

Neuron 3175 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: 0.9023. Min Range: -0.9023

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1589441 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1202350 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.8190. Min Act: -0.0000

Data Index: 176533 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1034897 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7682. Min Act: -0.0000

Data Index: 615612 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1398149 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1495147 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1334351 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6971. Min Act: -0.0000

Data Index: 262575 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1683838 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1545865 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1472405 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1425334 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6864. Min Act: -0.0000

Data Index: 598313 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1414423 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6661. Min Act: -0.0000

Data Index: 654015 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6562. Min Act: -0.0000

Data Index: 73790 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1243735 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1863820 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.9023. Min Range: -0.9023

Max Act: 0.6341. Min Act: -0.0000

Data Index: 416606 (The Pile)

Max Activating Token Index: 385