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

Dataset: The Pile

Neuron 3443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.8409. Min Act: -0.0000

Data Index: 83086 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.7378. Min Act: -0.0000

Data Index: 589852 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6872. Min Act: -0.0000

Data Index: 1641865 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6304. Min Act: -0.0000

Data Index: 18223 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6731. Min Act: -0.0000

Data Index: 565559 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6640. Min Act: -0.0000

Data Index: 545154 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6950. Min Act: -0.0000

Data Index: 940362 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6454. Min Act: -0.0000

Data Index: 828452 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.5932. Min Act: -0.0000

Data Index: 255579 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6867. Min Act: -0.0000

Data Index: 1711599 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1149129 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1664636 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6195. Min Act: -0.0000

Data Index: 1921216 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6202. Min Act: -0.0000

Data Index: 1477489 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6702. Min Act: -0.0000

Data Index: 913054 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6619. Min Act: -0.0000

Data Index: 1518745 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1144982 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.5651. Min Act: -0.0000

Data Index: 511298 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6027. Min Act: -0.0000

Data Index: 104527 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.6417. Min Act: -0.0000

Data Index: 743090 (The Pile)

Max Activating Token Index: 682