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

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

Neuron 4060 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0871. Min Range: -3.0871

Max Act: 3.0871. Min Act: -0.0000

Data Index: 1506233 (Python Code)

Max Activating Token Index: 746

Text #1

Max Range: 3.0871. Min Range: -3.0871

Max Act: 3.0265. Min Act: -0.0000

Data Index: 1642009 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 3.0871. Min Range: -3.0871

Max Act: 3.0177. Min Act: -0.0000

Data Index: 1458241 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.6141. Min Act: -0.0000

Data Index: 1629908 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 3.0871. Min Range: -3.0871

Max Act: 3.0179. Min Act: -0.0000

Data Index: 1406408 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8718. Min Act: -0.0000

Data Index: 1387848 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7214. Min Act: -0.0000

Data Index: 1588984 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8463. Min Act: -0.0000

Data Index: 1402540 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8118. Min Act: -0.0000

Data Index: 1485062 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1595727 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.6562. Min Act: -0.0000

Data Index: 1571394 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7382. Min Act: -0.0000

Data Index: 1506364 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.4754. Min Act: -0.0000

Data Index: 1489783 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.6106. Min Act: -0.0000

Data Index: 1599229 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8547. Min Act: -0.0000

Data Index: 1414578 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1620789 (Python Code)

Max Activating Token Index: 785

Text #16

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.5814. Min Act: -0.0000

Data Index: 1520747 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1558466 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1593391 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 3.0871. Min Range: -3.0871

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1427423 (Python Code)

Max Activating Token Index: 559