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

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

Neuron 3635 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0001

Data Index: 1650091 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1360000 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1521314 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1181962 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1389950 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1862. Min Act: -0.0001

Data Index: 1385432 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1446266 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1361041 (Python Code)

Max Activating Token Index: 909

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1455816 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1310557 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1649827 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1385858 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1413582 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1464898 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1482285 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1439252 (Python Code)

Max Activating Token Index: 991

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1543669 (Python Code)

Max Activating Token Index: 349

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1438499 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1578069 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1414883 (Python Code)

Max Activating Token Index: 135