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

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

Neuron 3758 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.1814. Min Act: -0.0000

Data Index: 885080 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.2945. Min Act: -0.0000

Data Index: 1327726 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.2742. Min Act: -0.0000

Data Index: 225184 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.3260. Min Act: -0.0000

Data Index: 1462132 (Python Code)

Max Activating Token Index: 662

Text #4

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.3363. Min Act: -0.0000

Data Index: 961302 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.3221. Min Act: -0.0000

Data Index: 534137 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.5493. Min Act: -0.0000

Data Index: 341613 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.1901. Min Act: -0.0000

Data Index: 558402 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.2555. Min Act: -0.0000

Data Index: 1367295 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.2559. Min Act: -0.0000

Data Index: 354305 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.1740. Min Act: -0.0000

Data Index: 162255 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1642086 (Python Code)

Max Activating Token Index: 724

Text #12

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.3010. Min Act: -0.0000

Data Index: 1289543 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.0894. Min Act: -0.0000

Data Index: 1328051 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.3222. Min Act: -0.0000

Data Index: 324303 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.2942. Min Act: -0.0000

Data Index: 1586422 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 2.5493. Min Range: -2.5493

Max Act: 1.8820. Min Act: -0.0000

Data Index: 1508289 (Python Code)

Max Activating Token Index: 685

Text #17

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.1127. Min Act: -0.0000

Data Index: 1312351 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1645443 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 2.5493. Min Range: -2.5493

Max Act: 2.0191. Min Act: -0.0000

Data Index: 1425595 (Python Code)

Max Activating Token Index: 195