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

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

Neuron 3062 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: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0002

Data Index: 473630 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1195971 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1328063 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0581. Min Act: -0.0002

Data Index: 818147 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0556. Min Act: -0.0002

Data Index: 139704 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0565. Min Act: -0.0002

Data Index: 285820 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0561. Min Act: -0.0002

Data Index: 35547 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0548. Min Act: -0.0002

Data Index: 986851 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1007852 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0552. Min Act: -0.0002

Data Index: 760426 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0553. Min Act: -0.0002

Data Index: 498156 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0543. Min Act: -0.0002

Data Index: 773785 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1137190 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1213525 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0547. Min Act: -0.0003

Data Index: 709633 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0539. Min Act: -0.0002

Data Index: 331108 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0535. Min Act: -0.0002

Data Index: 799037 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1282012 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0542. Min Act: -0.0002

Data Index: 700214 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0537. Min Act: -0.0002

Data Index: 530184 (C4 (Web Text))

Max Activating Token Index: 493