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

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

Neuron 3091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3292. Min Act: -0.0001

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1044335 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1349547 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2404. Min Act: -0.0001

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2126. Min Act: -0.0001

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2015. Min Act: -0.0001

Data Index: 490881 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1551127 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1500841 (Python Code)

Max Activating Token Index: 75

Text #8

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1641597 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1785. Min Act: -0.0001

Data Index: 778067 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1259422 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1879. Min Act: -0.0001

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1797. Min Act: -0.0001

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1479143 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1765. Min Act: -0.0001

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1112385 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1667. Min Act: -0.0001

Data Index: 586809 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1488471 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1478852 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1550454 (Python Code)

Max Activating Token Index: 428