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

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

Neuron 4161 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: 0.8380. Min Range: -0.8380

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1336558 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8036. Min Act: -0.0000

Data Index: 4925 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7990. Min Act: -0.0000

Data Index: 390588 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7675. Min Act: -0.0000

Data Index: 514106 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1050311 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8006. Min Act: -0.0000

Data Index: 419126 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7274. Min Act: -0.0000

Data Index: 122359 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7963. Min Act: -0.0000

Data Index: 714190 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7301. Min Act: -0.0000

Data Index: 188855 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7669. Min Act: -0.0000

Data Index: 764160 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7292. Min Act: -0.0000

Data Index: 285956 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8380. Min Act: -0.0000

Data Index: 698911 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7539. Min Act: -0.0000

Data Index: 967724 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7075. Min Act: -0.0000

Data Index: 476765 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1346517 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7742. Min Act: -0.0000

Data Index: 697556 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7944. Min Act: -0.0000

Data Index: 966739 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7693. Min Act: -0.0000

Data Index: 816181 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7845. Min Act: -0.0000

Data Index: 555964 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7278. Min Act: -0.0000

Data Index: 217622 (C4 (Web Text))

Max Activating Token Index: 536