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

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

Neuron 4144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.8538. Min Act: -0.0000

Data Index: 1189071 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.8052. Min Act: -0.0000

Data Index: 798990 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.3838. Min Act: -0.0000

Data Index: 130709 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.2264. Min Act: -0.0000

Data Index: 807536 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.1987. Min Act: -0.0000

Data Index: 733826 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.1697. Min Act: -0.0000

Data Index: 1162157 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.1341. Min Act: -0.0000

Data Index: 886709 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.0853. Min Act: -0.0000

Data Index: 175359 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.9302. Min Act: -0.0000

Data Index: 1336796 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.0416. Min Act: -0.0000

Data Index: 127474 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 3.8538. Min Range: -3.8538

Max Act: 2.0287. Min Act: -0.0000

Data Index: 867203 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.8706. Min Act: -0.0000

Data Index: 825711 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1178151 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.7212. Min Act: -0.0000

Data Index: 527319 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.6149. Min Act: -0.0000

Data Index: 1284079 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.7061. Min Act: -0.0000

Data Index: 242601 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.6984. Min Act: -0.0000

Data Index: 390931 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.4790. Min Act: -0.0000

Data Index: 922321 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.5491. Min Act: -0.0000

Data Index: 338465 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 3.8538. Min Range: -3.8538

Max Act: 1.5359. Min Act: -0.0000

Data Index: 385540 (C4 (Web Text))

Max Activating Token Index: 656