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

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

Neuron 866 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.7444. Min Act: -0.0000

Data Index: 527961 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.6469. Min Act: -0.0000

Data Index: 444442 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.6357. Min Act: -0.0000

Data Index: 769723 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5749. Min Act: -0.0000

Data Index: 242773 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.4900. Min Act: -0.0000

Data Index: 749085 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5728. Min Act: -0.0000

Data Index: 520494 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5428. Min Act: -0.0000

Data Index: 826242 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.6236. Min Act: -0.0000

Data Index: 90999 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1340201 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1338387 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5218. Min Act: -0.0000

Data Index: 509038 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.4457. Min Act: -0.0000

Data Index: 233262 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.4743. Min Act: -0.0000

Data Index: 198370 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.4625. Min Act: -0.0000

Data Index: 576706 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5243. Min Act: -0.0000

Data Index: 471788 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1106048 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.4128. Min Act: -0.0000

Data Index: 112856 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.4727. Min Act: -0.0000

Data Index: 1287032 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.2928. Min Act: -0.0000

Data Index: 101058 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.7444. Min Range: -1.7444

Max Act: 1.3617. Min Act: -0.0000

Data Index: 986592 (C4 (Web Text))

Max Activating Token Index: 524