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

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

Neuron 4308 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.5221. Min Act: -0.0000

Data Index: 392447 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.5042. Min Act: -0.0000

Data Index: 923587 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1702. Min Act: -0.0000

Data Index: 269670 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.2898. Min Act: -0.0000

Data Index: 605697 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.2081. Min Act: -0.0000

Data Index: 1006769 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1327190 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.2678. Min Act: -0.0000

Data Index: 666876 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1345694 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1998. Min Act: -0.0000

Data Index: 456421 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.2721. Min Act: -0.0000

Data Index: 215790 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1142. Min Act: -0.0000

Data Index: 320520 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.2508. Min Act: -0.0000

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1031. Min Act: -0.0000

Data Index: 827990 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1846. Min Act: -0.0000

Data Index: 838024 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1310216 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.0899. Min Act: -0.0000

Data Index: 78945 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1520. Min Act: -0.0000

Data Index: 32569 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1356. Min Act: -0.0000

Data Index: 101899 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1152. Min Act: -0.0000

Data Index: 90834 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.5221. Min Range: -1.5221

Max Act: 1.1658. Min Act: -0.0000

Data Index: 105105 (C4 (Web Text))

Max Activating Token Index: 853