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

Dataset: The Pile

Neuron 2204 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: 2.0530. Min Range: -2.0530

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1470467 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.3619. Min Act: -0.0000

Data Index: 103180 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1985999 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1706243 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.0716. Min Act: -0.0000

Data Index: 205163 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1824264 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1930856 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9956. Min Act: -0.0000

Data Index: 602392 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9679. Min Act: -0.0000

Data Index: 421575 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1373121 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 2.0530. Min Range: -2.0530

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1727780 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1085749 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1656325 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9256. Min Act: -0.0000

Data Index: 924717 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9471. Min Act: -0.0000

Data Index: 13070 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1105700 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1088735 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1793564 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.8921. Min Act: -0.0000

Data Index: 679357 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 2.0530. Min Range: -2.0530

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1012891 (The Pile)

Max Activating Token Index: 302