Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 776 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0451. Min Range: -1.0451

Max Act: 1.0451. Min Act: -0.0001

Data Index: 1609304 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1300876 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8462. Min Act: -0.0001

Data Index: 411082 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7593. Min Act: -0.0001

Data Index: 698629 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7839. Min Act: -0.0001

Data Index: 585326 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7387. Min Act: -0.0001

Data Index: 428704 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1556578 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6840. Min Act: -0.0001

Data Index: 1430200 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6384. Min Act: -0.0001

Data Index: 1368739 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1534002 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6647. Min Act: -0.0001

Data Index: 294054 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6925. Min Act: -0.0001

Data Index: 1498036 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7137. Min Act: -0.0001

Data Index: 137069 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7529. Min Act: -0.0001

Data Index: 595565 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6894. Min Act: -0.0001

Data Index: 644748 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6724. Min Act: -0.0001

Data Index: 973562 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1482251 (Python Code)

Max Activating Token Index: 932

Text #17

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6659. Min Act: -0.0001

Data Index: 1338254 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6995. Min Act: -0.0001

Data Index: 1406194 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1526927 (Python Code)

Max Activating Token Index: 342