Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 990 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1337323 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1290801 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1346254 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0566. Min Act: -0.0003

Data Index: 558848 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0545. Min Act: -0.0003

Data Index: 33580 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0534. Min Act: -0.0003

Data Index: 920653 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0550. Min Act: -0.0004

Data Index: 1312569 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0513. Min Act: -0.0003

Data Index: 372335 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0507. Min Act: -0.0004

Data Index: 993635 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0519. Min Act: -0.0002

Data Index: 894337 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0519. Min Act: -0.0003

Data Index: 522629 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0511. Min Act: -0.0003

Data Index: 686139 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0534. Min Act: -0.0003

Data Index: 605545 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0538. Min Act: -0.0003

Data Index: 998160 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1125136 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0511. Min Act: -0.0003

Data Index: 553377 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0513. Min Act: -0.0003

Data Index: 468754 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0504. Min Act: -0.0004

Data Index: 156741 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0508. Min Act: -0.0004

Data Index: 25470 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0487. Min Act: -0.0004

Data Index: 1242901 (C4 (Web Text))

Max Activating Token Index: 500