Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2023 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.8564. Min Act: -0.0000

Data Index: 18425 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.6776. Min Act: -0.0000

Data Index: 1756182 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.6820. Min Act: -0.0000

Data Index: 1301864 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.4508. Min Act: -0.0000

Data Index: 1189177 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.3608. Min Act: -0.0000

Data Index: 966503 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.3933. Min Act: -0.0000

Data Index: 1752142 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1438. Min Act: -0.0000

Data Index: 538737 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1175. Min Act: -0.0000

Data Index: 407133 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.2102. Min Act: -0.0000

Data Index: 1665483 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.2091. Min Act: -0.0000

Data Index: 1235508 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1243. Min Act: -0.0000

Data Index: 1458859 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1194. Min Act: -0.0000

Data Index: 157642 (The Pile)

Max Activating Token Index: 946

Text #12

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1121. Min Act: -0.0000

Data Index: 1624711 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.9571. Min Act: -0.0000

Data Index: 52251 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.0890. Min Act: -0.0000

Data Index: 733401 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.2397. Min Act: -0.0000

Data Index: 200189 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.2370. Min Act: -0.0000

Data Index: 1459309 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.0849. Min Act: -0.0000

Data Index: 512928 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.9187. Min Act: -0.0000

Data Index: 353707 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.0358. Min Act: -0.0000

Data Index: 1400096 (The Pile)

Max Activating Token Index: 990