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

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

Neuron 2628 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7378. Min Act: -0.0001

Data Index: 665992 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1362423 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7333. Min Act: -0.0001

Data Index: 1497954 (Python Code)

Max Activating Token Index: 535

Text #3

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1562362 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7485. Min Act: -0.0001

Data Index: 1432934 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1651032 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1520677 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1542200 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6954. Min Act: -0.0001

Data Index: 1520644 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6833. Min Act: -0.0001

Data Index: 1581049 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6616. Min Act: -0.0001

Data Index: 1391814 (Python Code)

Max Activating Token Index: 622

Text #11

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1636696 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6779. Min Act: -0.0001

Data Index: 1393733 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.7027. Min Act: -0.0001

Data Index: 1512515 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1462594 (Python Code)

Max Activating Token Index: 906

Text #15

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1374963 (Python Code)

Max Activating Token Index: 247

Text #16

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1564589 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.5925. Min Act: -0.0001

Data Index: 1611162 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6416. Min Act: -0.0001

Data Index: 1173522 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.7582. Min Range: -0.7582

Max Act: 0.6183. Min Act: -0.0001

Data Index: 1557152 (Python Code)

Max Activating Token Index: 149