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

Dataset: The Pile

Neuron 3694 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: 5.2161. Min Range: -5.2161

Max Act: 4.8705. Min Act: -0.0000

Data Index: 703636 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 5.2161. Min Range: -5.2161

Max Act: 5.2161. Min Act: -0.0000

Data Index: 499508 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 5.2161. Min Range: -5.2161

Max Act: 5.1445. Min Act: -0.0000

Data Index: 591046 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.5983. Min Act: -0.0000

Data Index: 1726413 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.6900. Min Act: -0.0000

Data Index: 443369 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.8829. Min Act: -0.0000

Data Index: 1418790 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.6541. Min Act: -0.0000

Data Index: 1724918 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.5764. Min Act: -0.0000

Data Index: 579360 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.6885. Min Act: -0.0000

Data Index: 1207334 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.2506. Min Act: -0.0000

Data Index: 1416029 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.2185. Min Act: -0.0000

Data Index: 895030 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.5132. Min Act: -0.0000

Data Index: 1932402 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.3304. Min Act: -0.0000

Data Index: 250904 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.1315. Min Act: -0.0000

Data Index: 315746 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.2263. Min Act: -0.0000

Data Index: 206088 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 5.2161. Min Range: -5.2161

Max Act: 3.8539. Min Act: -0.0000

Data Index: 1691513 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.3079. Min Act: -0.0000

Data Index: 1596747 (The Pile)

Max Activating Token Index: 787

Text #17

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.0017. Min Act: -0.0000

Data Index: 761058 (The Pile)

Max Activating Token Index: 827

Text #18

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.1496. Min Act: -0.0000

Data Index: 918271 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 5.2161. Min Range: -5.2161

Max Act: 4.3143. Min Act: -0.0000

Data Index: 1418525 (The Pile)

Max Activating Token Index: 769