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

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

Neuron 4871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.1564. Min Act: -0.0001

Data Index: 1387473 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.1659. Min Act: -0.0002

Data Index: 1485880 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.1485. Min Act: -0.0002

Data Index: 1608398 (Python Code)

Max Activating Token Index: 854

Text #3

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.1661. Min Act: -0.0001

Data Index: 1629756 (Python Code)

Max Activating Token Index: 545

Text #4

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.1002. Min Act: -0.0002

Data Index: 1427172 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.0486. Min Act: -0.0002

Data Index: 1611325 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.0450. Min Act: -0.0001

Data Index: 1376845 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 1.1661. Min Range: -1.1661

Max Act: 1.0393. Min Act: -0.0002

Data Index: 1395675 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.9914. Min Act: -0.0002

Data Index: 448952 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8748. Min Act: -0.0002

Data Index: 429003 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8518. Min Act: -0.0002

Data Index: 1402157 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8578. Min Act: -0.0002

Data Index: 1077156 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8492. Min Act: -0.0002

Data Index: 1426188 (Python Code)

Max Activating Token Index: 816

Text #13

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8507. Min Act: -0.0002

Data Index: 1624738 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8422. Min Act: -0.0002

Data Index: 1432582 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8192. Min Act: -0.0002

Data Index: 1290165 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8156. Min Act: -0.0002

Data Index: 1563270 (Python Code)

Max Activating Token Index: 100

Text #17

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8055. Min Act: -0.0002

Data Index: 1502319 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.8042. Min Act: -0.0002

Data Index: 20471 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.1661. Min Range: -1.1661

Max Act: 0.7783. Min Act: -0.0002

Data Index: 1403243 (Python Code)

Max Activating Token Index: 166