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

Dataset: The Pile

Neuron 1693 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.5760. Min Act: -0.0000

Data Index: 395781 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.5403. Min Act: -0.0000

Data Index: 954279 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.1221. Min Act: -0.0000

Data Index: 981930 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.0926. Min Act: -0.0000

Data Index: 718661 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1306579 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1616484 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1824112 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 1.5760. Min Range: -1.5760

Max Act: 1.0018. Min Act: -0.0000

Data Index: 605167 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9988. Min Act: -0.0000

Data Index: 440602 (The Pile)

Max Activating Token Index: 742

Text #9

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1420185 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9675. Min Act: -0.0000

Data Index: 969005 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9903. Min Act: -0.0000

Data Index: 818515 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1247403 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9104. Min Act: -0.0000

Data Index: 708582 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9039. Min Act: -0.0000

Data Index: 460797 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9014. Min Act: -0.0000

Data Index: 904018 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.8768. Min Act: -0.0000

Data Index: 97898 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1316072 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1823225 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 1.5760. Min Range: -1.5760

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1358445 (The Pile)

Max Activating Token Index: 689