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

Dataset: The Pile

Neuron 3957 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.4181. Min Act: -0.0000

Data Index: 327638 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.4407. Min Act: -0.0000

Data Index: 600406 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.4093. Min Act: -0.0000

Data Index: 559360 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1628520 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3632. Min Act: -0.0000

Data Index: 816313 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1814230 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1849769 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2779. Min Act: -0.0000

Data Index: 854141 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1826364 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1365198 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2905. Min Act: -0.0000

Data Index: 803275 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2584. Min Act: -0.0000

Data Index: 759017 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2614. Min Act: -0.0000

Data Index: 856847 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1291965 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2659. Min Act: -0.0000

Data Index: 161916 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1836637 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2531. Min Act: -0.0000

Data Index: 689172 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1523579 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1786683 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1666653 (The Pile)

Max Activating Token Index: 353