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

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

Neuron 3542 in Layer 1

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: 0.0551. Min Range: -0.0551

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1425577 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0002

Data Index: 833302 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1632252 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1522186 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1565404 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1518806 (Python Code)

Max Activating Token Index: 377

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0503. Min Act: -0.0002

Data Index: 342622 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1120611 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1625971 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1420255 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1653165 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1496844 (Python Code)

Max Activating Token Index: 215

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0483. Min Act: -0.0002

Data Index: 895432 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0467. Min Act: -0.0002

Data Index: 705577 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1409117 (Python Code)

Max Activating Token Index: 831

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0466. Min Act: -0.0002

Data Index: 580995 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1497803 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0468. Min Act: -0.0002

Data Index: 998631 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0462. Min Act: -0.0002

Data Index: 816129 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0456. Min Act: -0.0002

Data Index: 468912 (C4 (Web Text))

Max Activating Token Index: 111