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

Dataset: The Pile

Neuron 2401 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: 3.5891. Min Range: -3.5891

Max Act: 3.2888. Min Act: -0.0000

Data Index: 876776 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.5891. Min Act: -0.0000

Data Index: 578138 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.2289. Min Act: -0.0000

Data Index: 1450647 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.6892. Min Act: -0.0000

Data Index: 1510590 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.9388. Min Act: -0.0000

Data Index: 17651 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.9214. Min Act: -0.0000

Data Index: 791079 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.2613. Min Act: -0.0000

Data Index: 463462 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.9202. Min Act: -0.0000

Data Index: 1718291 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.3474. Min Act: -0.0000

Data Index: 161034 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.2226. Min Act: -0.0000

Data Index: 231716 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.8637. Min Act: -0.0000

Data Index: 1854698 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.5943. Min Act: -0.0000

Data Index: 1095734 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.2593. Min Act: -0.0000

Data Index: 1395375 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 3.5891. Min Range: -3.5891

Max Act: 3.0568. Min Act: -0.0000

Data Index: 460993 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.8575. Min Act: -0.0000

Data Index: 99498 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.5518. Min Act: -0.0000

Data Index: 425297 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.8285. Min Act: -0.0000

Data Index: 1619428 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.7992. Min Act: -0.0000

Data Index: 1360288 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.9144. Min Act: -0.0000

Data Index: 701076 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 3.5891. Min Range: -3.5891

Max Act: 2.9318. Min Act: -0.0000

Data Index: 218589 (The Pile)

Max Activating Token Index: 395