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

Dataset: The Pile

Neuron 3299 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: 0.5871. Min Range: -0.5871

Max Act: 0.5637. Min Act: -0.0000

Data Index: 835557 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5871. Min Act: -0.0000

Data Index: 820528 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5427. Min Act: -0.0000

Data Index: 107234 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5055. Min Act: -0.0000

Data Index: 61898 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1262932 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4625. Min Act: -0.0000

Data Index: 40499 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1527514 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1178145 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5395. Min Act: -0.0000

Data Index: 931715 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1363332 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1482771 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4263. Min Act: -0.0000

Data Index: 3271 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4625. Min Act: -0.0000

Data Index: 778457 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4281. Min Act: -0.0000

Data Index: 444338 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4199. Min Act: -0.0000

Data Index: 720343 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1162221 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4283. Min Act: -0.0000

Data Index: 538121 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4102. Min Act: -0.0000

Data Index: 359132 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4088. Min Act: -0.0000

Data Index: 602226 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4185. Min Act: -0.0000

Data Index: 613669 (The Pile)

Max Activating Token Index: 707