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

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

Neuron 2057 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7687. Min Range: -2.7687

Max Act: 2.3825. Min Act: -0.0000

Data Index: 533419 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 2.7687. Min Range: -2.7687

Max Act: 2.7687. Min Act: -0.0000

Data Index: 1640244 (Python Code)

Max Activating Token Index: 527

Text #2

Max Range: 2.7687. Min Range: -2.7687

Max Act: 2.2912. Min Act: -0.0000

Data Index: 1635814 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 2.7687. Min Range: -2.7687

Max Act: 2.1396. Min Act: -0.0000

Data Index: 1556150 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 2.7687. Min Range: -2.7687

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1581070 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 2.7687. Min Range: -2.7687

Max Act: 1.1637. Min Act: -0.0000

Data Index: 601507 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1488111 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1447537 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1404617 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1413715 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3468. Min Act: -0.0000

Data Index: 8617 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3481. Min Act: -0.0000

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3429. Min Act: -0.0000

Data Index: 409783 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1296308 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3265. Min Act: -0.0000

Data Index: 407610 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3167. Min Act: -0.0000

Data Index: 475239 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3151. Min Act: -0.0000

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.3111. Min Act: -0.0000

Data Index: 217632 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 2.7687. Min Range: -2.7687

Max Act: 0.2873. Min Act: -0.0000

Data Index: 641577 (C4 (Web Text))

Max Activating Token Index: 669