Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.4894. Min Act: -0.0000

Data Index: 1403669 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.3258. Min Act: -0.0000

Data Index: 351821 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.2463. Min Act: -0.0000

Data Index: 143664 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1726778 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1580. Min Act: -0.0000

Data Index: 967891 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1364618 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1594. Min Act: -0.0000

Data Index: 929338 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0723. Min Act: -0.0000

Data Index: 604460 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1714125 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1932229 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1984245 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1201080 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1215028 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9531. Min Act: -0.0000

Data Index: 399745 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0589. Min Act: -0.0000

Data Index: 239109 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.1471. Min Act: -0.0000

Data Index: 573730 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9717. Min Act: 0.0000

Data Index: 697847 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1957621 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0340. Min Act: -0.0000

Data Index: 450352 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0204. Min Act: -0.0000

Data Index: 740832 (The Pile)

Max Activating Token Index: 266