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

Dataset: The Pile

Neuron 4090 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: 4.0523. Min Range: -4.0523

Max Act: 4.0523. Min Act: -0.0000

Data Index: 1918312 (The Pile)

Max Activating Token Index: 599

Text #1

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.9307. Min Act: -0.0000

Data Index: 1910444 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.7649. Min Act: -0.0000

Data Index: 1789172 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.3156. Min Act: -0.0000

Data Index: 583526 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.5178. Min Act: -0.0000

Data Index: 1546846 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.6605. Min Act: -0.0000

Data Index: 1955748 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.8139. Min Act: -0.0000

Data Index: 97548 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.7331. Min Act: -0.0000

Data Index: 1294047 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.4251. Min Act: -0.0000

Data Index: 1696458 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.4291. Min Act: -0.0000

Data Index: 1718739 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.2106. Min Act: -0.0000

Data Index: 1956321 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.3566. Min Act: -0.0000

Data Index: 1094595 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.5063. Min Act: -0.0000

Data Index: 1736843 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.4841. Min Act: -0.0000

Data Index: 1270254 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.3211. Min Act: -0.0000

Data Index: 242854 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.4601. Min Act: -0.0000

Data Index: 1056669 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.2477. Min Act: -0.0000

Data Index: 543737 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.3994. Min Act: -0.0000

Data Index: 1378766 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.3881. Min Act: -0.0000

Data Index: 933622 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 4.0523. Min Range: -4.0523

Max Act: 3.3816. Min Act: -0.0000

Data Index: 412334 (The Pile)

Max Activating Token Index: 559