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

Dataset: The Pile

Neuron 4324 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1446053 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1892238 (The Pile)

Max Activating Token Index: 326

Text #2

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1671848 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1694615 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0672. Min Act: -0.0000

Data Index: 222247 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1777594 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1823815 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9681. Min Act: -0.0000

Data Index: 261984 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1146821 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0147. Min Act: -0.0000

Data Index: 31519 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1719567 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9570. Min Act: -0.0000

Data Index: 588242 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 1.3771. Min Range: -1.3771

Max Act: 1.0115. Min Act: -0.0000

Data Index: 377275 (The Pile)

Max Activating Token Index: 354

Text #13

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9511. Min Act: -0.0000

Data Index: 788531 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8918. Min Act: -0.0000

Data Index: 987185 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9413. Min Act: -0.0000

Data Index: 374040 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1732567 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8984. Min Act: -0.0000

Data Index: 23604 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.9014. Min Act: -0.0000

Data Index: 328437 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 1.3771. Min Range: -1.3771

Max Act: 0.8339. Min Act: -0.0000

Data Index: 104540 (The Pile)

Max Activating Token Index: 192