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

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

Neuron 554 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1838. Min Range: -5.1838

Max Act: 5.1838. Min Act: -0.0001

Data Index: 1599758 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 5.1838. Min Range: -5.1838

Max Act: 4.1991. Min Act: -0.0001

Data Index: 1470593 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 5.1838. Min Range: -5.1838

Max Act: 4.0648. Min Act: -0.0000

Data Index: 1653268 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 5.1838. Min Range: -5.1838

Max Act: 4.1442. Min Act: -0.0000

Data Index: 1609690 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.9386. Min Act: -0.0001

Data Index: 1517486 (Python Code)

Max Activating Token Index: 500

Text #5

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.2774. Min Act: -0.0001

Data Index: 1594488 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 5.1838. Min Range: -5.1838

Max Act: 4.0222. Min Act: -0.0001

Data Index: 1494631 (Python Code)

Max Activating Token Index: 530

Text #7

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.3842. Min Act: -0.0000

Data Index: 1518863 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.6870. Min Act: -0.0000

Data Index: 1554738 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.5164. Min Act: -0.0000

Data Index: 1517787 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.3875. Min Act: -0.0000

Data Index: 1365852 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.2685. Min Act: -0.0001

Data Index: 1546146 (Python Code)

Max Activating Token Index: 919

Text #12

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.1511. Min Act: -0.0000

Data Index: 1528098 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 5.1838. Min Range: -5.1838

Max Act: 3.1062. Min Act: -0.0000

Data Index: 1381680 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 5.1838. Min Range: -5.1838

Max Act: 2.6008. Min Act: -0.0000

Data Index: 1474015 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 5.1838. Min Range: -5.1838

Max Act: 2.6524. Min Act: -0.0001

Data Index: 1583187 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 5.1838. Min Range: -5.1838

Max Act: 2.7442. Min Act: -0.0000

Data Index: 1432821 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 5.1838. Min Range: -5.1838

Max Act: 2.6093. Min Act: -0.0001

Data Index: 1634207 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 5.1838. Min Range: -5.1838

Max Act: 2.8456. Min Act: -0.0000

Data Index: 1401595 (Python Code)

Max Activating Token Index: 458

Text #19

Max Range: 5.1838. Min Range: -5.1838

Max Act: 2.6015. Min Act: -0.0001

Data Index: 1422864 (Python Code)

Max Activating Token Index: 775