Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1976 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1161. Min Range: -1.1161

Max Act: 1.1161. Min Act: 0.0001

Data Index: 1638820 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.9133. Min Act: 0.0000

Data Index: 1611734 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1508888 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1452373 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1521950 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1605151 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1646389 (Python Code)

Max Activating Token Index: 571

Text #7

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1568993 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1604515 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1627940 (Python Code)

Max Activating Token Index: 227

Text #10

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1388209 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1448846 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7370. Min Act: 0.0001

Data Index: 1368955 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1625507 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1561906 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1586866 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1441580 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1459102 (Python Code)

Max Activating Token Index: 517

Text #18

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1547440 (Python Code)

Max Activating Token Index: 638

Text #19

Max Range: 1.1161. Min Range: -1.1161

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1646333 (Python Code)

Max Activating Token Index: 11