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

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

Neuron 541 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.3002. Min Act: -0.0001

Data Index: 1036393 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.3970. Min Act: -0.0000

Data Index: 214652 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.4347. Min Act: -0.0001

Data Index: 1157957 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1039799 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.1218. Min Act: -0.0001

Data Index: 271158 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.1328. Min Act: -0.0001

Data Index: 674281 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.2316. Min Act: -0.0001

Data Index: 1233861 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0757. Min Act: -0.0001

Data Index: 311884 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.1275. Min Act: -0.0001

Data Index: 482115 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0380. Min Act: -0.0000

Data Index: 198148 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0088. Min Act: -0.0001

Data Index: 836446 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0430. Min Act: -0.0001

Data Index: 812770 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1240434 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.1306. Min Act: -0.0000

Data Index: 88255 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0086. Min Act: -0.0001

Data Index: 1002588 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.4347. Min Range: -1.4347

Max Act: 0.9944. Min Act: -0.0001

Data Index: 1358543 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.4347. Min Range: -1.4347

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1305720 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0507. Min Act: -0.0001

Data Index: 1205091 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 1.4347. Min Range: -1.4347

Max Act: 1.0289. Min Act: -0.0000

Data Index: 444920 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.4347. Min Range: -1.4347

Max Act: 0.9977. Min Act: -0.0001

Data Index: 507198 (C4 (Web Text))

Max Activating Token Index: 165