Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1898 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.4855. Min Act: -0.0001

Data Index: 469401 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.2799. Min Act: -0.0001

Data Index: 474104 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3033. Min Act: -0.0001

Data Index: 969462 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.0174. Min Act: -0.0001

Data Index: 1300843 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.1441. Min Act: -0.0001

Data Index: 220086 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.9710. Min Act: -0.0001

Data Index: 395329 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.1982. Min Act: -0.0001

Data Index: 333612 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.0321. Min Act: -0.0001

Data Index: 907409 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.1633. Min Act: -0.0001

Data Index: 1259590 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.1425. Min Act: -0.0001

Data Index: 1293226 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.9574. Min Act: -0.0001

Data Index: 285541 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.9843. Min Act: -0.0001

Data Index: 1048712 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.8012. Min Act: -0.0001

Data Index: 839282 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.0274. Min Act: -0.0001

Data Index: 738174 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.8660. Min Act: -0.0001

Data Index: 42681 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.6930. Min Act: -0.0001

Data Index: 1345273 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.9546. Min Act: -0.0001

Data Index: 1002813 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.8215. Min Act: -0.0001

Data Index: 1021025 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.8109. Min Act: -0.0001

Data Index: 1021448 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.4855. Min Range: -3.4855

Max Act: 2.7910. Min Act: -0.0001

Data Index: 492643 (C4 (Web Text))

Max Activating Token Index: 472