Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3736 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1558253 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0606. Min Act: -0.0002

Data Index: 980816 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1333717 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1459194 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1581421 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0549. Min Act: -0.0002

Data Index: 714162 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0566. Min Act: -0.0002

Data Index: 97471 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0544. Min Act: -0.0002

Data Index: 403005 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0521. Min Act: -0.0002

Data Index: 80323 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1478772 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1629780 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1117518 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0503. Min Act: -0.0002

Data Index: 213762 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0538. Min Act: -0.0002

Data Index: 230646 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1408199 (Python Code)

Max Activating Token Index: 909

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1487258 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0502. Min Act: -0.0002

Data Index: 679374 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1082587 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0512. Min Act: -0.0002

Data Index: 80447 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1444915 (Python Code)

Max Activating Token Index: 1023