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

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

Neuron 3869 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1423247 (Python Code)

Max Activating Token Index: 663

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1495846 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1531262 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1478212 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0423. Min Act: -0.0003

Data Index: 423825 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1625852 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1393337 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1298436 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0310. Min Act: -0.0003

Data Index: 197819 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0298. Min Act: -0.0003

Data Index: 197048 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0296. Min Act: -0.0003

Data Index: 462057 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0294. Min Act: -0.0002

Data Index: 804773 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0291. Min Act: -0.0003

Data Index: 940529 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1530193 (Python Code)

Max Activating Token Index: 613

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0290. Min Act: -0.0003

Data Index: 427167 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0290. Min Act: -0.0003

Data Index: 175958 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0289. Min Act: -0.0003

Data Index: 661768 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0288. Min Act: -0.0003

Data Index: 887470 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0286. Min Act: -0.0003

Data Index: 771718 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0274. Min Act: -0.0003

Data Index: 266757 (C4 (Web Text))

Max Activating Token Index: 441