Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1854 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1369808 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1579240 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1421083 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1511786 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1540529 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1570272 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1561061 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1611559 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1570716 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1405041 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1488343 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1606397 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1415433 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1438470 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1621467 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1643570 (Python Code)

Max Activating Token Index: 470

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1440246 (Python Code)

Max Activating Token Index: 557

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1580108 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1512775 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1655453 (Python Code)

Max Activating Token Index: 1023