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

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

Neuron 1434 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: 1.3197. Min Range: -1.3197

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1456139 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2659. Min Act: -0.0000

Data Index: 499184 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1364763 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1404795 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1461359 (Python Code)

Max Activating Token Index: 694

Text #5

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1602212 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1617552 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1619752 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1561239 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1616253 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1525331 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1446110 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1610161 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1437525 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1557891 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1389302 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.8583. Min Act: -0.0000

Data Index: 63572 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9531. Min Act: -0.0001

Data Index: 1615099 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1644252 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 1.3197. Min Range: -1.3197

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1652860 (Python Code)

Max Activating Token Index: 710