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

Dataset: The Pile

Neuron 2937 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: 0.6966. Min Range: -0.6966

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1389016 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.6289. Min Act: -0.0000

Data Index: 600451 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1064854 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5746. Min Act: -0.0000

Data Index: 353108 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1378972 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1672725 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1370660 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1178453 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1591635 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1523552 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4954. Min Act: -0.0000

Data Index: 943319 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1271523 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.5087. Min Act: -0.0000

Data Index: 169781 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4860. Min Act: -0.0000

Data Index: 971270 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1332950 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4713. Min Act: -0.0000

Data Index: 938280 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4527. Min Act: -0.0000

Data Index: 556738 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1744977 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4577. Min Act: -0.0000

Data Index: 917617 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.6966. Min Range: -0.6966

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1762417 (The Pile)

Max Activating Token Index: 778