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

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

Neuron 1830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6751. Min Act: -0.0001

Data Index: 1374590 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1600567 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6906. Min Act: -0.0001

Data Index: 1656165 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6285. Min Act: -0.0001

Data Index: 1501769 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.7508. Min Act: -0.0001

Data Index: 1488027 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1552578 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6417. Min Act: -0.0001

Data Index: 1552180 (Python Code)

Max Activating Token Index: 583

Text #7

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1409354 (Python Code)

Max Activating Token Index: 825

Text #8

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6226. Min Act: -0.0001

Data Index: 1413329 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6671. Min Act: -0.0001

Data Index: 1446717 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6393. Min Act: -0.0001

Data Index: 1415540 (Python Code)

Max Activating Token Index: 83

Text #11

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6738. Min Act: -0.0001

Data Index: 1379781 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6327. Min Act: -0.0001

Data Index: 1596586 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6196. Min Act: -0.0001

Data Index: 1627716 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5879. Min Act: -0.0002

Data Index: 1409406 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1380447 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1562113 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6305. Min Act: -0.0001

Data Index: 1653568 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6257. Min Act: -0.0001

Data Index: 1362755 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6452. Min Act: -0.0001

Data Index: 1442175 (Python Code)

Max Activating Token Index: 947