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

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

Neuron 4274 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2833. Min Act: -0.0000

Data Index: 886611 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2757. Min Act: -0.0000

Data Index: 81757 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2709. Min Act: -0.0000

Data Index: 381311 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2680. Min Act: -0.0000

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2348. Min Act: -0.0000

Data Index: 627861 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2566. Min Act: -0.0000

Data Index: 202613 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2650. Min Act: -0.0000

Data Index: 663610 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2543. Min Act: -0.0000

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2294. Min Act: -0.0000

Data Index: 479522 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2440. Min Act: -0.0000

Data Index: 270497 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2271. Min Act: -0.0000

Data Index: 944789 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2264. Min Act: -0.0000

Data Index: 437368 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2335. Min Act: -0.0000

Data Index: 437837 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2361. Min Act: -0.0000

Data Index: 652271 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2249. Min Act: -0.0000

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2233. Min Act: -0.0000

Data Index: 856574 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2283. Min Act: -0.0000

Data Index: 417910 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2169. Min Act: -0.0000

Data Index: 159512 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2094. Min Act: -0.0000

Data Index: 677638 (C4 (Web Text))

Max Activating Token Index: 647