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

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

Neuron 4452 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: 0.5613. Min Range: -0.5613

Max Act: 0.5613. Min Act: -0.0000

Data Index: 322008 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1622519 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1195591 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1379965 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1084488 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3738. Min Act: -0.0000

Data Index: 610802 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1365165 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3675. Min Act: -0.0000

Data Index: 329365 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1390606 (Python Code)

Max Activating Token Index: 303

Text #9

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1492791 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1456135 (Python Code)

Max Activating Token Index: 405

Text #11

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3586. Min Act: -0.0000

Data Index: 217750 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1563749 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3311. Min Act: -0.0000

Data Index: 233844 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1480382 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1559826 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1011951 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1213291 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3157. Min Act: -0.0000

Data Index: 848317 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.5613. Min Range: -0.5613

Max Act: 0.3053. Min Act: -0.0000

Data Index: 925543 (C4 (Web Text))

Max Activating Token Index: 576