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

Dataset: The Pile

Neuron 2982 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: 1.0849. Min Range: -1.0849

Max Act: 1.0849. Min Act: -0.0000

Data Index: 795 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8771. Min Act: -0.0000

Data Index: 695295 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1052994 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1064565 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8172. Min Act: -0.0000

Data Index: 115174 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8926. Min Act: -0.0000

Data Index: 46799 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7845. Min Act: -0.0000

Data Index: 255765 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1766392 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8666. Min Act: -0.0000

Data Index: 963448 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1991876 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1629952 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1026677 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1650691 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1050323 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8893. Min Act: -0.0000

Data Index: 404996 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7423. Min Act: -0.0000

Data Index: 242763 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7794. Min Act: -0.0000

Data Index: 358444 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1074100 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1112114 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.6846. Min Act: -0.0000

Data Index: 735163 (The Pile)

Max Activating Token Index: 600