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

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

Neuron 5718 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: 3.3302. Min Range: -3.3302

Max Act: 3.3302. Min Act: -0.0000

Data Index: 1012589 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 3.3302. Min Range: -3.3302

Max Act: 3.3131. Min Act: -0.0000

Data Index: 942379 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.3302. Min Range: -3.3302

Max Act: 3.1477. Min Act: -0.0000

Data Index: 388359 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.3302. Min Range: -3.3302

Max Act: 3.0308. Min Act: -0.0000

Data Index: 919620 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.8974. Min Act: -0.0000

Data Index: 440370 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.8487. Min Act: -0.0000

Data Index: 850132 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.8194. Min Act: -0.0000

Data Index: 1015151 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.6611. Min Act: -0.0000

Data Index: 658816 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.7943. Min Act: -0.0000

Data Index: 7543 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.8856. Min Act: -0.0000

Data Index: 848492 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.6192. Min Act: -0.0000

Data Index: 374471 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.6405. Min Act: -0.0000

Data Index: 200979 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.4529. Min Act: -0.0000

Data Index: 195694 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.5709. Min Act: -0.0000

Data Index: 1041908 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.5433. Min Act: -0.0000

Data Index: 537918 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.6612. Min Act: -0.0000

Data Index: 1289578 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.3708. Min Act: -0.0000

Data Index: 666432 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.3517. Min Act: -0.0000

Data Index: 223758 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.4553. Min Act: -0.0000

Data Index: 428608 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.3302. Min Range: -3.3302

Max Act: 2.3268. Min Act: -0.0000

Data Index: 897299 (C4 (Web Text))

Max Activating Token Index: 501