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

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

Neuron 3699 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: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1437573 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1558032 (Python Code)

Max Activating Token Index: 923

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0565. Min Act: -0.0002

Data Index: 701593 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0559. Min Act: -0.0002

Data Index: 579239 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0544. Min Act: -0.0002

Data Index: 899258 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0542. Min Act: -0.0002

Data Index: 148761 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1225626 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0530. Min Act: -0.0002

Data Index: 352242 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1655879 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0525. Min Act: -0.0002

Data Index: 69689 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1346792 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0523. Min Act: -0.0002

Data Index: 743708 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0502. Min Act: -0.0002

Data Index: 15413 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0500. Min Act: -0.0002

Data Index: 682040 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0504. Min Act: -0.0002

Data Index: 64900 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0486. Min Act: -0.0003

Data Index: 806213 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0504. Min Act: -0.0002

Data Index: 961426 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0497. Min Act: -0.0002

Data Index: 673203 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0492. Min Act: -0.0002

Data Index: 798351 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1103158 (C4 (Web Text))

Max Activating Token Index: 629