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

Dataset: The Pile

Neuron 170 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: 5.0591. Min Range: -5.0591

Max Act: 5.0591. Min Act: -0.0000

Data Index: 1136366 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.0913. Min Act: -0.0000

Data Index: 509662 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.3397. Min Act: -0.0000

Data Index: 1305674 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.2242. Min Act: -0.0000

Data Index: 1716573 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.2952. Min Act: -0.0000

Data Index: 409710 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.1089. Min Act: -0.0000

Data Index: 1821828 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.3987. Min Act: -0.0000

Data Index: 1344293 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.4270. Min Act: -0.0000

Data Index: 1742642 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.0407. Min Act: -0.0000

Data Index: 660621 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.2277. Min Act: -0.0000

Data Index: 815934 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.3224. Min Act: -0.0000

Data Index: 140988 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.8325. Min Act: -0.0000

Data Index: 848711 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.3340. Min Act: -0.0000

Data Index: 1013577 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.9866. Min Act: -0.0000

Data Index: 1077291 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.5438. Min Act: -0.0000

Data Index: 861910 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.2226. Min Act: -0.0000

Data Index: 1411206 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 5.0591. Min Range: -5.0591

Max Act: 4.0277. Min Act: -0.0000

Data Index: 1709094 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.8258. Min Act: -0.0000

Data Index: 1765143 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 5.0591. Min Range: -5.0591

Max Act: 3.7642. Min Act: -0.0000

Data Index: 1568385 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 5.0591. Min Range: -5.0591

Max Act: 2.8324. Min Act: -0.0000

Data Index: 1427827 (The Pile)

Max Activating Token Index: 762