Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.7642. Min Act: -0.0001

Data Index: 521699 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.2244. Min Act: -0.0001

Data Index: 764515 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.6303. Min Act: -0.0001

Data Index: 1278494 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.1271. Min Act: -0.0001

Data Index: 1565853 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.1129. Min Act: -0.0001

Data Index: 196191 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.1539. Min Act: -0.0001

Data Index: 528199 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.9833. Min Act: -0.0001

Data Index: 1420397 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.2060. Min Act: -0.0001

Data Index: 461609 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.8965. Min Act: -0.0001

Data Index: 774126 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.7642. Min Range: -3.7642

Max Act: 3.0692. Min Act: -0.0001

Data Index: 1322469 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.9163. Min Act: -0.0001

Data Index: 1433519 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.5990. Min Act: -0.0001

Data Index: 62851 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.5331. Min Act: -0.0001

Data Index: 589090 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.6889. Min Act: -0.0001

Data Index: 1095084 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.8133. Min Act: -0.0001

Data Index: 81650 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.9256. Min Act: -0.0001

Data Index: 579998 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.5379. Min Act: -0.0001

Data Index: 1302854 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.7181. Min Act: -0.0001

Data Index: 726907 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.5545. Min Act: -0.0001

Data Index: 1096753 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.7642. Min Range: -3.7642

Max Act: 2.4164. Min Act: -0.0001

Data Index: 483444 (C4 (Web Text))

Max Activating Token Index: 414