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

Dataset: The Pile

Neuron 528 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0114. Min Range: -1.0114

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1713542 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9376. Min Act: -0.0000

Data Index: 63047 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1515642 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1432673 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8678. Min Act: -0.0000

Data Index: 792919 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8453. Min Act: -0.0000

Data Index: 791773 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1307852 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8480. Min Act: 0.0000

Data Index: 902247 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7600. Min Act: -0.0000

Data Index: 805307 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1050584 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8254. Min Act: 0.0000

Data Index: 494778 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1239464 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8222. Min Act: -0.0000

Data Index: 584817 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8067. Min Act: -0.0000

Data Index: 347471 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7786. Min Act: -0.0000

Data Index: 337263 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1304504 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7451. Min Act: -0.0000

Data Index: 321054 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7667. Min Act: -0.0000

Data Index: 262943 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7644. Min Act: -0.0000

Data Index: 146632 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1709721 (The Pile)

Max Activating Token Index: 952