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

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

Neuron 5437 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.2754. Min Act: -0.0000

Data Index: 168355 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.2650. Min Act: -0.0000

Data Index: 873939 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.1260. Min Act: -0.0000

Data Index: 518988 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.1214. Min Act: -0.0000

Data Index: 493501 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.0239. Min Act: -0.0000

Data Index: 565029 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.0136. Min Act: -0.0000

Data Index: 377518 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.2754. Min Range: -1.2754

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1015275 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.9699. Min Act: -0.0000

Data Index: 131491 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1245334 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.9168. Min Act: -0.0000

Data Index: 832304 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1153825 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.9537. Min Act: -0.0000

Data Index: 259299 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8964. Min Act: -0.0000

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1092415 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8387. Min Act: -0.0000

Data Index: 234512 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1149880 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8427. Min Act: -0.0000

Data Index: 699617 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.7785. Min Act: -0.0000

Data Index: 950725 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8071. Min Act: 0.0000

Data Index: 111848 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.2754. Min Range: -1.2754

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1003147 (C4 (Web Text))

Max Activating Token Index: 181