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

Dataset: The Pile

Neuron 4672 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: 1.3859. Min Range: -1.3859

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1552937 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.1608. Min Act: -0.0000

Data Index: 539301 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1257588 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0376. Min Act: -0.0000

Data Index: 240401 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1813169 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0598. Min Act: -0.0000

Data Index: 626025 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9992. Min Act: -0.0000

Data Index: 829932 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.3859. Min Range: -1.3859

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1426944 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9273. Min Act: -0.0000

Data Index: 814716 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9271. Min Act: -0.0000

Data Index: 490861 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8409. Min Act: -0.0000

Data Index: 762647 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8929. Min Act: -0.0000

Data Index: 647871 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1244123 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9060. Min Act: -0.0000

Data Index: 439342 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1689143 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1793959 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1812192 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8520. Min Act: -0.0000

Data Index: 885858 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1693210 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 1.3859. Min Range: -1.3859

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1226766 (The Pile)

Max Activating Token Index: 492