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

Dataset: The Pile

Neuron 4496 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.1412. Min Act: -0.0000

Data Index: 296392 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0238. Min Act: -0.0000

Data Index: 318325 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0260. Min Act: -0.0000

Data Index: 738571 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9962. Min Act: -0.0000

Data Index: 864915 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1094959 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9121. Min Act: -0.0000

Data Index: 528518 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7870. Min Act: -0.0000

Data Index: 768442 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1217717 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7728. Min Act: -0.0000

Data Index: 928998 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1182849 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7802. Min Act: -0.0000

Data Index: 573464 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1806408 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7945. Min Act: -0.0000

Data Index: 875011 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7173. Min Act: -0.0000

Data Index: 573864 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7205. Min Act: -0.0000

Data Index: 616422 (The Pile)

Max Activating Token Index: 96

Text #15

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1765603 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7585. Min Act: -0.0000

Data Index: 282991 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1510497 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1077637 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.6794. Min Act: -0.0000

Data Index: 710154 (The Pile)

Max Activating Token Index: 399