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

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

Neuron 4522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1386766 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8499. Min Act: -0.0001

Data Index: 1460135 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1364878 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1434403 (Python Code)

Max Activating Token Index: 334

Text #4

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1551184 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1650055 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1487198 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1643069 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1427316 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1465301 (Python Code)

Max Activating Token Index: 448

Text #10

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8118. Min Act: -0.0001

Data Index: 1434871 (Python Code)

Max Activating Token Index: 825

Text #11

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7990. Min Act: -0.0001

Data Index: 1434897 (Python Code)

Max Activating Token Index: 982

Text #12

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1444198 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7918. Min Act: -0.0001

Data Index: 1499242 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7653. Min Act: -0.0001

Data Index: 1420723 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1509157 (Python Code)

Max Activating Token Index: 789

Text #16

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1366758 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1525663 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1444133 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1466265 (Python Code)

Max Activating Token Index: 305