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

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

Neuron 4178 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.6279. Min Act: -0.0000

Data Index: 1619878 (Python Code)

Max Activating Token Index: 985

Text #1

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.3442. Min Act: -0.0000

Data Index: 1492137 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.4581. Min Act: -0.0000

Data Index: 626656 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.5648. Min Act: -0.0000

Data Index: 1534969 (Python Code)

Max Activating Token Index: 623

Text #4

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1527. Min Act: -0.0000

Data Index: 1597252 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1259. Min Act: -0.0000

Data Index: 1511581 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1168. Min Act: -0.0000

Data Index: 529117 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1752. Min Act: -0.0000

Data Index: 256548 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1644. Min Act: -0.0000

Data Index: 80991 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1640. Min Act: -0.0000

Data Index: 916002 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1182. Min Act: -0.0000

Data Index: 905680 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.0011. Min Act: -0.0000

Data Index: 833184 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1245. Min Act: -0.0000

Data Index: 1395113 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 3.6279. Min Range: -3.6279

Max Act: 2.9641. Min Act: -0.0000

Data Index: 1444353 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 3.6279. Min Range: -3.6279

Max Act: 2.6869. Min Act: -0.0000

Data Index: 1481847 (Python Code)

Max Activating Token Index: 525

Text #15

Max Range: 3.6279. Min Range: -3.6279

Max Act: 2.9625. Min Act: -0.0000

Data Index: 1044460 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 3.6279. Min Range: -3.6279

Max Act: 2.8090. Min Act: -0.0000

Data Index: 576064 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.1039. Min Act: -0.0000

Data Index: 1344259 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.2133. Min Act: -0.0000

Data Index: 1418799 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 3.6279. Min Range: -3.6279

Max Act: 3.0852. Min Act: -0.0000

Data Index: 1545090 (Python Code)

Max Activating Token Index: 50