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

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

Neuron 2018 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: 1.2846. Min Range: -1.2846

Max Act: 1.2846. Min Act: -0.0000

Data Index: 922240 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.2846. Min Range: -1.2846

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1095679 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.2846. Min Range: -1.2846

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1206939 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9782. Min Act: -0.0000

Data Index: 955960 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1027120 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9856. Min Act: -0.0000

Data Index: 932287 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9667. Min Act: 0.0001

Data Index: 612391 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9528. Min Act: 0.0001

Data Index: 1335250 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9036. Min Act: -0.0000

Data Index: 848362 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8586. Min Act: 0.0000

Data Index: 798585 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8715. Min Act: -0.0000

Data Index: 227468 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8301. Min Act: -0.0000

Data Index: 959029 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8340. Min Act: -0.0000

Data Index: 774479 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9047. Min Act: -0.0000

Data Index: 522537 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.9234. Min Act: 0.0001

Data Index: 897232 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1266602 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1124741 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.7952. Min Act: -0.0000

Data Index: 707816 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.2846. Min Range: -1.2846

Max Act: 0.8454. Min Act: -0.0000

Data Index: 670039 (C4 (Web Text))

Max Activating Token Index: 961