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

Dataset: The Pile

Neuron 1291 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.2738. Min Act: -0.0000

Data Index: 889806 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 5.2738. Min Range: -5.2738

Max Act: 5.0580. Min Act: -0.0000

Data Index: 196788 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.9095. Min Act: -0.0000

Data Index: 193299 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.8502. Min Act: -0.0000

Data Index: 1238982 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.4193. Min Act: -0.0000

Data Index: 355251 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6871. Min Act: -0.0000

Data Index: 1141540 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6530. Min Act: -0.0000

Data Index: 811630 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.4713. Min Act: -0.0000

Data Index: 974205 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.6223. Min Act: -0.0000

Data Index: 1771896 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.2851. Min Act: -0.0000

Data Index: 162591 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.3147. Min Act: -0.0000

Data Index: 551465 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.4933. Min Act: -0.0000

Data Index: 1732192 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.4743. Min Act: -0.0000

Data Index: 568728 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.4640. Min Act: -0.0000

Data Index: 1140939 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.0363. Min Act: -0.0000

Data Index: 50639 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.2896. Min Act: -0.0000

Data Index: 1914894 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 5.2738. Min Range: -5.2738

Max Act: 3.9176. Min Act: -0.0000

Data Index: 264196 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.2882. Min Act: -0.0000

Data Index: 1881149 (The Pile)

Max Activating Token Index: 678

Text #18

Max Range: 5.2738. Min Range: -5.2738

Max Act: 3.9213. Min Act: -0.0000

Data Index: 1465340 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 5.2738. Min Range: -5.2738

Max Act: 4.0405. Min Act: -0.0000

Data Index: 413936 (The Pile)

Max Activating Token Index: 670