Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1498 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.4029. Min Act: -0.0000

Data Index: 463747 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.3425. Min Act: -0.0000

Data Index: 377310 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.1939. Min Act: 0.0000

Data Index: 1061340 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.1720. Min Act: -0.0000

Data Index: 705039 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.2866. Min Act: -0.0000

Data Index: 46455 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.0553. Min Act: -0.0000

Data Index: 1241164 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.1371. Min Act: -0.0000

Data Index: 952750 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.0667. Min Act: -0.0000

Data Index: 471936 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.2950. Min Act: -0.0000

Data Index: 1009071 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.1191. Min Act: -0.0000

Data Index: 1345015 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.9034. Min Act: -0.0000

Data Index: 65252 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 2.4029. Min Range: -2.4029

Max Act: 2.0013. Min Act: -0.0000

Data Index: 857858 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.9581. Min Act: -0.0000

Data Index: 931817 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.9787. Min Act: -0.0000

Data Index: 894179 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.8231. Min Act: -0.0000

Data Index: 1045099 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.8988. Min Act: -0.0000

Data Index: 53531 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.7470. Min Act: -0.0000

Data Index: 1214120 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.8298. Min Act: -0.0000

Data Index: 1077398 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.8111. Min Act: -0.0000

Data Index: 965406 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 2.4029. Min Range: -2.4029

Max Act: 1.8338. Min Act: -0.0000

Data Index: 606411 (C4 (Web Text))

Max Activating Token Index: 793