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

Dataset: The Pile

Neuron 1311 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: 1.4520. Min Range: -1.4520

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1751321 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3956. Min Act: -0.0000

Data Index: 186951 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.4520. Min Act: -0.0000

Data Index: 886567 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3943. Min Act: -0.0000

Data Index: 896731 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1665453 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3138. Min Act: -0.0000

Data Index: 639270 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3837. Min Act: -0.0000

Data Index: 553328 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2965. Min Act: -0.0000

Data Index: 400210 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3783. Min Act: -0.0000

Data Index: 110690 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3289. Min Act: -0.0000

Data Index: 600731 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3718. Min Act: -0.0000

Data Index: 117726 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3547. Min Act: -0.0000

Data Index: 454938 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0760. Min Act: -0.0000

Data Index: 354298 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1402792 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1006643 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 1.4520. Min Range: -1.4520

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1390683 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1590202 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3102. Min Act: -0.0000

Data Index: 219783 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2709. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1458672 (The Pile)

Max Activating Token Index: 1000