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

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

Neuron 3218 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: 1.4538. Min Range: -1.4538

Max Act: 1.4538. Min Act: -0.0000

Data Index: 556087 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.2836. Min Act: -0.0000

Data Index: 948167 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1151364 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1054140 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.1687. Min Act: -0.0000

Data Index: 726525 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1313842 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.1480. Min Act: -0.0000

Data Index: 195732 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.1272. Min Act: -0.0000

Data Index: 225695 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0842. Min Act: -0.0000

Data Index: 984677 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1187111 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0861. Min Act: -0.0000

Data Index: 747045 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0324. Min Act: -0.0000

Data Index: 816665 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.1265. Min Act: -0.0000

Data Index: 266525 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0780. Min Act: -0.0000

Data Index: 348179 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0437. Min Act: -0.0000

Data Index: 205874 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0039. Min Act: -0.0000

Data Index: 778225 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0247. Min Act: -0.0000

Data Index: 246654 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1307184 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.4538. Min Range: -1.4538

Max Act: 0.9512. Min Act: -0.0000

Data Index: 857951 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.4538. Min Range: -1.4538

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1292352 (C4 (Web Text))

Max Activating Token Index: 786