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

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

Neuron 4157 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: 3.6957. Min Range: -3.6957

Max Act: 3.5619. Min Act: -0.0001

Data Index: 1569494 (Python Code)

Max Activating Token Index: 252

Text #1

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.5230. Min Act: -0.0001

Data Index: 1545471 (Python Code)

Max Activating Token Index: 124

Text #2

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.1454. Min Act: -0.0001

Data Index: 1649735 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.2536. Min Act: -0.0001

Data Index: 1606136 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.4420. Min Act: -0.0001

Data Index: 1389546 (Python Code)

Max Activating Token Index: 418

Text #5

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.2645. Min Act: -0.0001

Data Index: 1515977 (Python Code)

Max Activating Token Index: 580

Text #6

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.8517. Min Act: -0.0001

Data Index: 1432805 (Python Code)

Max Activating Token Index: 409

Text #7

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.3773. Min Act: -0.0001

Data Index: 1389852 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.6957. Min Act: -0.0001

Data Index: 1570712 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.2303. Min Act: -0.0001

Data Index: 1580152 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.3583. Min Act: -0.0001

Data Index: 1623937 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.8369. Min Act: -0.0001

Data Index: 1654760 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.2228. Min Act: -0.0001

Data Index: 1573420 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.9033. Min Act: -0.0001

Data Index: 1610013 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.0187. Min Act: -0.0001

Data Index: 1453041 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.8678. Min Act: -0.0001

Data Index: 1439359 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.9772. Min Act: -0.0001

Data Index: 1461021 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 3.6957. Min Range: -3.6957

Max Act: 3.1027. Min Act: -0.0001

Data Index: 1619383 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.9239. Min Act: -0.0001

Data Index: 1432296 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 3.6957. Min Range: -3.6957

Max Act: 2.9292. Min Act: -0.0001

Data Index: 1602756 (Python Code)

Max Activating Token Index: 129