Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2053 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.8339. Min Act: -0.0001

Data Index: 1042354 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.8032. Min Act: -0.0001

Data Index: 675885 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1099357 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7948. Min Act: -0.0001

Data Index: 56547 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7615. Min Act: -0.0001

Data Index: 34540 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7075. Min Act: -0.0000

Data Index: 878770 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7399. Min Act: -0.0000

Data Index: 93152 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1167555 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6688. Min Act: -0.0001

Data Index: 1316003 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6681. Min Act: -0.0001

Data Index: 1085310 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6594. Min Act: -0.0000

Data Index: 928943 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6541. Min Act: -0.0001

Data Index: 1276214 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6504. Min Act: -0.0000

Data Index: 808873 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6285. Min Act: -0.0001

Data Index: 136370 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6836. Min Act: -0.0001

Data Index: 942191 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6336. Min Act: -0.0000

Data Index: 918842 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6158. Min Act: -0.0000

Data Index: 514440 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6278. Min Act: -0.0000

Data Index: 207510 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6252. Min Act: -0.0000

Data Index: 20379 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1259892 (C4 (Web Text))

Max Activating Token Index: 425