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

Dataset: The Pile

Neuron 1796 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0772. Min Range: -3.0772

Max Act: 3.0743. Min Act: -0.0000

Data Index: 439539 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 3.0772. Min Range: -3.0772

Max Act: 3.0772. Min Act: -0.0000

Data Index: 1770571 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.9799. Min Act: -0.0000

Data Index: 674665 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.8832. Min Act: -0.0000

Data Index: 628888 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.8727. Min Act: -0.0000

Data Index: 179013 (The Pile)

Max Activating Token Index: 212

Text #5

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6506. Min Act: -0.0000

Data Index: 242151 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.7260. Min Act: -0.0000

Data Index: 780537 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6898. Min Act: -0.0000

Data Index: 73164 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6639. Min Act: -0.0000

Data Index: 1214180 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6360. Min Act: -0.0000

Data Index: 430680 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.5022. Min Act: -0.0000

Data Index: 1633692 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.7240. Min Act: -0.0000

Data Index: 1562500 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6841. Min Act: -0.0000

Data Index: 94324 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.5404. Min Act: -0.0000

Data Index: 850008 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6313. Min Act: -0.0000

Data Index: 1269170 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.6036. Min Act: -0.0000

Data Index: 450512 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.4338. Min Act: -0.0000

Data Index: 1070117 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.4440. Min Act: -0.0000

Data Index: 1529292 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.4324. Min Act: -0.0000

Data Index: 913709 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 3.0772. Min Range: -3.0772

Max Act: 2.4053. Min Act: -0.0000

Data Index: 1178078 (The Pile)

Max Activating Token Index: 264