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

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

Neuron 1789 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.6971. Min Act: -0.0000

Data Index: 1379165 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.8770. Min Act: -0.0000

Data Index: 1533824 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 6.1989. Min Range: -6.1989

Max Act: 6.1989. Min Act: -0.0000

Data Index: 1515019 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.9654. Min Act: -0.0000

Data Index: 1387486 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3781. Min Act: -0.0000

Data Index: 1499229 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3930. Min Act: -0.0000

Data Index: 1403292 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3560. Min Act: -0.0000

Data Index: 1493216 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.5935. Min Act: -0.0000

Data Index: 1563187 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3187. Min Act: -0.0000

Data Index: 1513322 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3539. Min Act: -0.0000

Data Index: 1627914 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3865. Min Act: -0.0000

Data Index: 1477774 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.3253. Min Act: -0.0000

Data Index: 1401911 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.0454. Min Act: -0.0000

Data Index: 1486000 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.2915. Min Act: -0.0000

Data Index: 1557029 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.0474. Min Act: -0.0000

Data Index: 1484371 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 6.1989. Min Range: -6.1989

Max Act: 4.8171. Min Act: -0.0000

Data Index: 1609717 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.0924. Min Act: -0.0000

Data Index: 1428074 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 6.1989. Min Range: -6.1989

Max Act: 5.0648. Min Act: -0.0000

Data Index: 1601870 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 6.1989. Min Range: -6.1989

Max Act: 4.8544. Min Act: -0.0000

Data Index: 1533486 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 6.1989. Min Range: -6.1989

Max Act: 4.8423. Min Act: -0.0000

Data Index: 1468088 (Python Code)

Max Activating Token Index: 103