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

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

Neuron 1538 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.4457. Min Act: -0.0000

Data Index: 1578655 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.3554. Min Act: -0.0000

Data Index: 1575526 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.4540. Min Act: -0.0000

Data Index: 1392266 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.4178. Min Act: -0.0000

Data Index: 1466883 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.4118. Min Act: -0.0000

Data Index: 1367827 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.3672. Min Act: -0.0000

Data Index: 1410877 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.2596. Min Act: -0.0000

Data Index: 1640906 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.0229. Min Act: -0.0000

Data Index: 1544197 (Python Code)

Max Activating Token Index: 861

Text #8

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1404136 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.8352. Min Act: -0.0000

Data Index: 1407423 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.9415. Min Act: -0.0000

Data Index: 1393226 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.9089. Min Act: -0.0000

Data Index: 1483537 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 2.4540. Min Range: -2.4540

Max Act: 2.0066. Min Act: -0.0000

Data Index: 1570825 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1477373 (Python Code)

Max Activating Token Index: 359

Text #14

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.9970. Min Act: -0.0000

Data Index: 1374590 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.9970. Min Act: -0.0000

Data Index: 1463835 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.8788. Min Act: -0.0000

Data Index: 1560585 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.8655. Min Act: -0.0000

Data Index: 1523079 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1360191 (Python Code)

Max Activating Token Index: 921

Text #19

Max Range: 2.4540. Min Range: -2.4540

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1374556 (Python Code)

Max Activating Token Index: 19