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

Dataset: The Pile

Neuron 407 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: 0.6269. Min Range: -0.6269

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1316664 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5708. Min Act: -0.0000

Data Index: 772322 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5565. Min Act: -0.0000

Data Index: 280537 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1496088 (The Pile)

Max Activating Token Index: 821

Text #4

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5250. Min Act: -0.0000

Data Index: 530813 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5225. Min Act: -0.0000

Data Index: 495967 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5208. Min Act: -0.0000

Data Index: 617931 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4837. Min Act: -0.0000

Data Index: 254215 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5168. Min Act: -0.0000

Data Index: 543443 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1856980 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1585723 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5354. Min Act: -0.0000

Data Index: 874351 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1924237 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4845. Min Act: -0.0000

Data Index: 780610 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4814. Min Act: -0.0000

Data Index: 415831 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1178670 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.5248. Min Act: -0.0000

Data Index: 320155 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4379. Min Act: -0.0000

Data Index: 167961 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4642. Min Act: -0.0000

Data Index: 457572 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.6269. Min Range: -0.6269

Max Act: 0.4661. Min Act: -0.0000

Data Index: 61637 (The Pile)

Max Activating Token Index: 526