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

Dataset: The Pile

Neuron 3637 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: 0.8706. Min Range: -0.8706

Max Act: 0.8706. Min Act: -0.0000

Data Index: 755432 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1264118 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1333250 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6310. Min Act: -0.0000

Data Index: 84669 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1830917 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6093. Min Act: -0.0000

Data Index: 603176 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6353. Min Act: -0.0000

Data Index: 120299 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5307. Min Act: -0.0000

Data Index: 59928 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1910398 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6636. Min Act: -0.0000

Data Index: 499471 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6082. Min Act: -0.0000

Data Index: 333824 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1096 (The Pile)

Max Activating Token Index: 299

Text #12

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1838989 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5675. Min Act: -0.0000

Data Index: 730376 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5317. Min Act: -0.0000

Data Index: 431582 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1012748 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5248. Min Act: -0.0000

Data Index: 354089 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5411. Min Act: -0.0000

Data Index: 101050 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5367. Min Act: -0.0000

Data Index: 986028 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.4837. Min Act: -0.0000

Data Index: 910653 (The Pile)

Max Activating Token Index: 710