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

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

Neuron 2834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1311408 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1012275 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.2228. Min Act: -0.0000

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1932. Min Act: -0.0000

Data Index: 237920 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.2094. Min Act: -0.0000

Data Index: 487446 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1471. Min Act: -0.0000

Data Index: 490247 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1464. Min Act: -0.0000

Data Index: 149918 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.2128. Min Act: -0.0000

Data Index: 668115 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1709. Min Act: -0.0000

Data Index: 762489 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1185. Min Act: -0.0000

Data Index: 778835 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1453. Min Act: -0.0000

Data Index: 463657 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1615. Min Act: -0.0000

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1182032 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0449. Min Act: -0.0000

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1236944 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0636. Min Act: -0.0000

Data Index: 140350 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0071. Min Act: -0.0000

Data Index: 330436 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1304001 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1079266 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.5053. Min Range: -1.5053

Max Act: 1.0153. Min Act: -0.0000

Data Index: 153453 (C4 (Web Text))

Max Activating Token Index: 497