Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2771. Min Act: -0.0001

Data Index: 547119 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1022382 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2513. Min Act: -0.0001

Data Index: 485877 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1104639 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2670. Min Act: -0.0001

Data Index: 529086 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2461. Min Act: -0.0001

Data Index: 298553 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2103. Min Act: -0.0001

Data Index: 815304 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2155. Min Act: -0.0001

Data Index: 865514 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1051109 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2071. Min Act: -0.0001

Data Index: 138878 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1137298 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1315221 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2132. Min Act: -0.0001

Data Index: 389188 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2009. Min Act: -0.0001

Data Index: 827271 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1885. Min Act: -0.0001

Data Index: 114152 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2007. Min Act: -0.0001

Data Index: 740807 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2026. Min Act: -0.0001

Data Index: 361090 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1900. Min Act: -0.0001

Data Index: 280226 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1957. Min Act: -0.0001

Data Index: 166848 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1856. Min Act: -0.0001

Data Index: 567022 (C4 (Web Text))

Max Activating Token Index: 574