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

Dataset: The Pile

Neuron 950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.8014. Min Act: -0.0000

Data Index: 593484 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.8541. Min Act: -0.0000

Data Index: 91668 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.8137. Min Act: -0.0000

Data Index: 490089 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1857372 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1194128 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1903212 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6816. Min Act: -0.0000

Data Index: 350830 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1297481 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6975. Min Act: -0.0000

Data Index: 462954 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6984. Min Act: -0.0000

Data Index: 239630 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6528. Min Act: -0.0000

Data Index: 842997 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6767. Min Act: -0.0000

Data Index: 679254 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6918. Min Act: -0.0000

Data Index: 66229 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7051. Min Act: -0.0000

Data Index: 831875 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6418. Min Act: -0.0000

Data Index: 516978 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6721. Min Act: -0.0000

Data Index: 528987 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1249873 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1462802 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1698618 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1805382 (The Pile)

Max Activating Token Index: 112