Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.4491. Min Act: -0.0001

Data Index: 27122 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3980. Min Act: -0.0001

Data Index: 744368 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.4372. Min Act: -0.0001

Data Index: 609808 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3619. Min Act: -0.0001

Data Index: 1176748 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.3063. Min Act: -0.0001

Data Index: 1127096 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2714. Min Act: -0.0001

Data Index: 687449 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2665. Min Act: -0.0001

Data Index: 1102658 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2679. Min Act: -0.0001

Data Index: 1405895 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2911. Min Act: -0.0001

Data Index: 1406510 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.2051. Min Act: -0.0001

Data Index: 886496 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1592. Min Act: -0.0001

Data Index: 633942 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1858. Min Act: -0.0001

Data Index: 310678 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1817. Min Act: -0.0001

Data Index: 558121 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1446. Min Act: -0.0001

Data Index: 739468 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1645. Min Act: -0.0001

Data Index: 609214 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1559. Min Act: -0.0001

Data Index: 550430 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1782. Min Act: -0.0001

Data Index: 1109597 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.0616. Min Act: -0.0001

Data Index: 1221371 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.0598. Min Act: -0.0001

Data Index: 1140757 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.4491. Min Range: -1.4491

Max Act: 1.1600. Min Act: -0.0001

Data Index: 725370 (C4 (Web Text))

Max Activating Token Index: 307