Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5813. Min Range: -5.5813

Max Act: 5.5813. Min Act: -0.0000

Data Index: 157091 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 5.5813. Min Range: -5.5813

Max Act: 5.0854. Min Act: -0.0000

Data Index: 432529 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 5.5813. Min Range: -5.5813

Max Act: 4.6682. Min Act: -0.0000

Data Index: 753071 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 5.5813. Min Range: -5.5813

Max Act: 3.7887. Min Act: -0.0000

Data Index: 974162 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 5.5813. Min Range: -5.5813

Max Act: 3.7020. Min Act: -0.0000

Data Index: 579564 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 5.5813. Min Range: -5.5813

Max Act: 3.5079. Min Act: -0.0000

Data Index: 342953 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 5.5813. Min Range: -5.5813

Max Act: 3.3214. Min Act: -0.0000

Data Index: 1330021 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.9930. Min Act: -0.0000

Data Index: 518759 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.7984. Min Act: -0.0000

Data Index: 907971 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.5260. Min Act: -0.0000

Data Index: 101241 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.4347. Min Act: -0.0000

Data Index: 1335858 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1136128 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.4746. Min Act: -0.0000

Data Index: 111507 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.2726. Min Act: -0.0000

Data Index: 619261 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.2326. Min Act: -0.0000

Data Index: 397968 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.2642. Min Act: -0.0000

Data Index: 1326788 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.1540. Min Act: -0.0000

Data Index: 1166445 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.0093. Min Act: -0.0000

Data Index: 882748 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.0923. Min Act: -0.0000

Data Index: 1302477 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 5.5813. Min Range: -5.5813

Max Act: 2.0593. Min Act: -0.0000

Data Index: 218760 (C4 (Web Text))

Max Activating Token Index: 656