Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3535 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4446. Min Act: -0.0001

Data Index: 1394953 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4838. Min Act: -0.0001

Data Index: 1365674 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4197. Min Act: -0.0001

Data Index: 1462962 (Python Code)

Max Activating Token Index: 712

Text #3

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4500. Min Act: -0.0001

Data Index: 1428357 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2661. Min Act: -0.0000

Data Index: 381432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3763. Min Act: -0.0001

Data Index: 1615880 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3270. Min Act: -0.0001

Data Index: 1579864 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3139. Min Act: -0.0001

Data Index: 1387118 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2865. Min Act: -0.0001

Data Index: 1379530 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3173. Min Act: -0.0000

Data Index: 359773 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3156. Min Act: -0.0001

Data Index: 1539908 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2442. Min Act: -0.0001

Data Index: 1539077 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3234. Min Act: -0.0001

Data Index: 1257704 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3782. Min Act: -0.0001

Data Index: 1522696 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2290. Min Act: -0.0001

Data Index: 1445998 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2428. Min Act: -0.0001

Data Index: 1490987 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1147. Min Act: -0.0000

Data Index: 39845 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2156. Min Act: -0.0001

Data Index: 1616033 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.1475. Min Act: -0.0001

Data Index: 1116765 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2843. Min Act: -0.0000

Data Index: 848659 (C4 (Web Text))

Max Activating Token Index: 948