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

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

Neuron 674 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.7380. Min Act: -0.0003

Data Index: 1460757 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.6871. Min Act: -0.0003

Data Index: 1496161 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.5072. Min Act: -0.0003

Data Index: 1500055 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4888. Min Act: -0.0003

Data Index: 1620894 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4611. Min Act: -0.0003

Data Index: 1418727 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4295. Min Act: -0.0003

Data Index: 1652007 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4300. Min Act: -0.0003

Data Index: 1575018 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4277. Min Act: -0.0003

Data Index: 1621816 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4242. Min Act: -0.0003

Data Index: 1393936 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4440. Min Act: -0.0003

Data Index: 1478595 (Python Code)

Max Activating Token Index: 229

Text #10

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4317. Min Act: -0.0003

Data Index: 1609875 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4242. Min Act: -0.0003

Data Index: 1581351 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3429. Min Act: -0.0003

Data Index: 1595634 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3710. Min Act: -0.0003

Data Index: 1656168 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.4050. Min Act: -0.0004

Data Index: 1427744 (Python Code)

Max Activating Token Index: 804

Text #15

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3297. Min Act: -0.0003

Data Index: 1461219 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3891. Min Act: -0.0003

Data Index: 1573224 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3618. Min Act: -0.0003

Data Index: 1422661 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3214. Min Act: -0.0003

Data Index: 1401773 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 1.7380. Min Range: -1.7380

Max Act: 1.3546. Min Act: -0.0003

Data Index: 1495409 (Python Code)

Max Activating Token Index: 936