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

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

Neuron 1843 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: 1.0913. Min Range: -1.0913

Max Act: 1.0913. Min Act: -0.0001

Data Index: 799204 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8772. Min Act: -0.0001

Data Index: 1047643 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8905. Min Act: -0.0001

Data Index: 1059323 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8914. Min Act: -0.0001

Data Index: 733655 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9367. Min Act: -0.0001

Data Index: 464017 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8300. Min Act: -0.0001

Data Index: 805718 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9099. Min Act: -0.0001

Data Index: 586578 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.0913. Min Range: -1.0913

Max Act: 1.0186. Min Act: -0.0001

Data Index: 180440 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.9301. Min Act: -0.0001

Data Index: 1169753 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8794. Min Act: -0.0001

Data Index: 692350 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8189. Min Act: -0.0001

Data Index: 590368 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8442. Min Act: -0.0001

Data Index: 1353258 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7399. Min Act: -0.0000

Data Index: 112537 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8038. Min Act: -0.0001

Data Index: 1358380 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1168118 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7762. Min Act: -0.0001

Data Index: 868967 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.8085. Min Act: -0.0001

Data Index: 987613 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7243. Min Act: -0.0001

Data Index: 591440 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7641. Min Act: -0.0001

Data Index: 162269 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 1.0913. Min Range: -1.0913

Max Act: 0.7479. Min Act: -0.0001

Data Index: 164892 (C4 (Web Text))

Max Activating Token Index: 432