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

Dataset: The Pile

Neuron 192 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: 1.2810. Min Range: -1.2810

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1371245 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1135245 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.1339. Min Act: -0.0000

Data Index: 137141 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1345208 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9660. Min Act: -0.0000

Data Index: 856444 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1626158 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9463. Min Act: -0.0000

Data Index: 980932 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9877. Min Act: -0.0000

Data Index: 639460 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9092. Min Act: -0.0000

Data Index: 694705 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9237. Min Act: -0.0000

Data Index: 262002 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9373. Min Act: -0.0000

Data Index: 105564 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9487. Min Act: -0.0000

Data Index: 60701 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8642. Min Act: -0.0000

Data Index: 975941 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1644304 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1695208 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1835673 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8167. Min Act: -0.0000

Data Index: 267417 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8783. Min Act: -0.0000

Data Index: 463757 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8981. Min Act: -0.0000

Data Index: 575418 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1736460 (The Pile)

Max Activating Token Index: 749