Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 571 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2441. Min Act: -0.0003

Data Index: 1377640 (Python Code)

Max Activating Token Index: 433

Text #1

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2331. Min Act: -0.0003

Data Index: 1590825 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2345. Min Act: -0.0003

Data Index: 1444847 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2232. Min Act: -0.0003

Data Index: 1385575 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2220. Min Act: -0.0003

Data Index: 1427249 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2042. Min Act: -0.0003

Data Index: 1518300 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1986. Min Act: -0.0003

Data Index: 1390902 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2011. Min Act: -0.0003

Data Index: 1515732 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1917. Min Act: -0.0003

Data Index: 1547335 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1982. Min Act: -0.0003

Data Index: 1624946 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1801. Min Act: -0.0003

Data Index: 1485240 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1753. Min Act: -0.0003

Data Index: 1494271 (Python Code)

Max Activating Token Index: 974

Text #12

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1755. Min Act: -0.0003

Data Index: 1611346 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1730. Min Act: -0.0003

Data Index: 1541212 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1710. Min Act: -0.0003

Data Index: 1397677 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1692. Min Act: -0.0003

Data Index: 1644530 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1748. Min Act: -0.0003

Data Index: 1377519 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1724. Min Act: -0.0003

Data Index: 1648229 (Python Code)

Max Activating Token Index: 237

Text #18

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1658. Min Act: -0.0003

Data Index: 1647962 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1655. Min Act: -0.0003

Data Index: 1557412 (Python Code)

Max Activating Token Index: 516