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

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

Neuron 216 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3576. Min Range: -6.3576

Max Act: 6.3576. Min Act: -0.0000

Data Index: 1425480 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.7823. Min Act: -0.0000

Data Index: 1585701 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.7869. Min Act: -0.0000

Data Index: 1363305 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.3699. Min Act: -0.0000

Data Index: 1538946 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.3187. Min Act: -0.0000

Data Index: 1442563 (Python Code)

Max Activating Token Index: 829

Text #5

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.6768. Min Act: -0.0000

Data Index: 1493842 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.4853. Min Act: -0.0000

Data Index: 1478431 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.6256. Min Act: -0.0000

Data Index: 1372857 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.4198. Min Act: -0.0000

Data Index: 1639745 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.4287. Min Act: -0.0000

Data Index: 1636483 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.3899. Min Act: -0.0000

Data Index: 1645157 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.5742. Min Act: -0.0000

Data Index: 1535858 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.1922. Min Act: -0.0000

Data Index: 1370329 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.1324. Min Act: -0.0000

Data Index: 1646304 (Python Code)

Max Activating Token Index: 692

Text #14

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.1331. Min Act: -0.0000

Data Index: 1581742 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.5201. Min Act: -0.0000

Data Index: 1606326 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.4993. Min Act: -0.0000

Data Index: 1499447 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.4815. Min Act: -0.0000

Data Index: 1434021 (Python Code)

Max Activating Token Index: 520

Text #18

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.2963. Min Act: -0.0000

Data Index: 1365741 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 6.3576. Min Range: -6.3576

Max Act: 5.2876. Min Act: -0.0000

Data Index: 1550239 (Python Code)

Max Activating Token Index: 451