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

Dataset: The Pile

Neuron 2585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.2576. Min Act: -0.0000

Data Index: 856496 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.2713. Min Act: -0.0000

Data Index: 157197 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.2090. Min Act: -0.0000

Data Index: 1249080 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.1476. Min Act: -0.0000

Data Index: 762365 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.9643. Min Act: -0.0000

Data Index: 1627728 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.9044. Min Act: -0.0000

Data Index: 421440 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.8880. Min Act: -0.0000

Data Index: 1592633 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.0459. Min Act: -0.0000

Data Index: 48125 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.9797. Min Act: -0.0000

Data Index: 488275 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.8220. Min Act: -0.0000

Data Index: 596141 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.7538. Min Act: -0.0000

Data Index: 1135710 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.7397. Min Act: -0.0000

Data Index: 219662 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.7257. Min Act: -0.0000

Data Index: 652250 (The Pile)

Max Activating Token Index: 384

Text #13

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.0048. Min Act: -0.0000

Data Index: 149777 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.6740. Min Act: -0.0000

Data Index: 10776 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.8476. Min Act: -0.0000

Data Index: 172756 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 4.2713. Min Range: -4.2713

Max Act: 4.1594. Min Act: -0.0000

Data Index: 1264304 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.8525. Min Act: -0.0000

Data Index: 1112948 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.5210. Min Act: -0.0000

Data Index: 648659 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 4.2713. Min Range: -4.2713

Max Act: 3.7454. Min Act: -0.0000

Data Index: 1669802 (The Pile)

Max Activating Token Index: 73