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

Dataset: The Pile

Neuron 1714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1943. Min Range: -5.1943

Max Act: 5.1943. Min Act: -0.0000

Data Index: 1954370 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.6891. Min Act: -0.0000

Data Index: 1493817 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.6220. Min Act: -0.0000

Data Index: 832539 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.7628. Min Act: -0.0000

Data Index: 1296239 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.7693. Min Act: -0.0000

Data Index: 1242975 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.5246. Min Act: -0.0000

Data Index: 1049553 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.4803. Min Act: -0.0000

Data Index: 1042687 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.6224. Min Act: -0.0000

Data Index: 605265 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.4690. Min Act: -0.0000

Data Index: 1073173 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.4264. Min Act: -0.0000

Data Index: 1661410 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.5471. Min Act: -0.0000

Data Index: 1924796 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.3968. Min Act: -0.0000

Data Index: 1142570 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.4116. Min Act: -0.0000

Data Index: 38000 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.5354. Min Act: -0.0000

Data Index: 1890338 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.5413. Min Act: -0.0000

Data Index: 708558 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.5088. Min Act: -0.0000

Data Index: 1102308 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.4879. Min Act: -0.0000

Data Index: 1950002 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.3236. Min Act: -0.0000

Data Index: 1558411 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.3143. Min Act: -0.0000

Data Index: 1672554 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 5.1943. Min Range: -5.1943

Max Act: 4.4533. Min Act: -0.0000

Data Index: 879184 (The Pile)

Max Activating Token Index: 90