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

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

Neuron 3262 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.1460. Min Act: -0.0001

Data Index: 1526558 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1380497 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0211. Min Act: -0.0001

Data Index: 1447378 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 1.1460. Min Range: -1.1460

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1527187 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9640. Min Act: -0.0001

Data Index: 1555051 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1365276 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1371363 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9079. Min Act: 0.0003

Data Index: 1629820 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8937. Min Act: -0.0001

Data Index: 1508945 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1403181 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8209. Min Act: -0.0001

Data Index: 1610420 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8290. Min Act: -0.0000

Data Index: 67128 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8488. Min Act: 0.0003

Data Index: 1492402 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9235. Min Act: -0.0001

Data Index: 1447639 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1368326 (Python Code)

Max Activating Token Index: 137

Text #15

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1498938 (Python Code)

Max Activating Token Index: 407

Text #16

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.9067. Min Act: 0.0003

Data Index: 1531732 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8513. Min Act: -0.0001

Data Index: 5647 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1610245 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 1.1460. Min Range: -1.1460

Max Act: 0.8428. Min Act: -0.0000

Data Index: 920072 (C4 (Web Text))

Max Activating Token Index: 25