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

Dataset: The Pile

Neuron 3714 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: 0.4485. Min Range: -0.4485

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1401294 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1880758 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1317359 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1833756 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1609612 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3501. Min Act: -0.0000

Data Index: 544493 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1392047 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3456. Min Act: -0.0000

Data Index: 903133 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3644. Min Act: -0.0000

Data Index: 255510 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2979. Min Act: -0.0000

Data Index: 261930 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1072367 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3775. Min Act: -0.0000

Data Index: 12918 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1474397 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1324405 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3119. Min Act: -0.0000

Data Index: 305320 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1568242 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1370702 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1444336 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1672506 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.2862. Min Act: -0.0000

Data Index: 510371 (The Pile)

Max Activating Token Index: 527