Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1697 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.1423. Min Act: -0.0001

Data Index: 820656 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.2401. Min Act: -0.0001

Data Index: 373333 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.1100. Min Act: -0.0001

Data Index: 679432 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.0669. Min Act: -0.0001

Data Index: 792219 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.0706. Min Act: -0.0001

Data Index: 553228 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9565. Min Act: -0.0001

Data Index: 1155174 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.0395. Min Act: -0.0001

Data Index: 1232920 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.0194. Min Act: -0.0001

Data Index: 449612 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9740. Min Act: -0.0001

Data Index: 277102 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.2401. Min Range: -1.2401

Max Act: 1.0196. Min Act: -0.0001

Data Index: 867464 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9831. Min Act: -0.0001

Data Index: 601151 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9463. Min Act: -0.0001

Data Index: 489983 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9081. Min Act: -0.0001

Data Index: 981799 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.9266. Min Act: -0.0001

Data Index: 753408 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8435. Min Act: -0.0001

Data Index: 89560 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8900. Min Act: -0.0001

Data Index: 488492 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8900. Min Act: -0.0001

Data Index: 532901 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8900. Min Act: -0.0001

Data Index: 730035 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8900. Min Act: -0.0001

Data Index: 310385 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.2401. Min Range: -1.2401

Max Act: 0.8900. Min Act: -0.0001

Data Index: 226540 (C4 (Web Text))

Max Activating Token Index: 2