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

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

Neuron 1399 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: 0.5146. Min Range: -0.5146

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1429112 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4803. Min Act: 0.0000

Data Index: 865522 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4060. Min Act: -0.0000

Data Index: 77565 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4401. Min Act: -0.0000

Data Index: 48054 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4571. Min Act: 0.0000

Data Index: 638059 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1364314 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1559826 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1349699 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1582337 (Python Code)

Max Activating Token Index: 854

Text #9

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1200534 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1484555 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3813. Min Act: 0.0000

Data Index: 937546 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1492791 (Python Code)

Max Activating Token Index: 402

Text #13

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1563797 (Python Code)

Max Activating Token Index: 413

Text #14

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3558. Min Act: -0.0000

Data Index: 746595 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1532089 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1379926 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1229093 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1525041 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1372253 (Python Code)

Max Activating Token Index: 1008