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

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

Neuron 5810 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1015594 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.1025. Min Act: -0.0000

Data Index: 570439 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1007168 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0769. Min Act: -0.0000

Data Index: 525128 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0456. Min Act: -0.0000

Data Index: 527455 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9997. Min Act: -0.0000

Data Index: 80940 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1196385 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9799. Min Act: -0.0000

Data Index: 382622 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0053. Min Act: -0.0000

Data Index: 110019 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9441. Min Act: -0.0000

Data Index: 389960 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1203511 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9486. Min Act: -0.0000

Data Index: 882848 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.1428. Min Range: -1.1428

Max Act: 1.0114. Min Act: -0.0000

Data Index: 460156 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9961. Min Act: -0.0000

Data Index: 233714 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9542. Min Act: -0.0000

Data Index: 729744 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9774. Min Act: -0.0000

Data Index: 617386 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1286201 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9429. Min Act: -0.0000

Data Index: 38892 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1202823 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.1428. Min Range: -1.1428

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1064942 (C4 (Web Text))

Max Activating Token Index: 35