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

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

Neuron 3792 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: 1.1447. Min Range: -1.1447

Max Act: 1.1447. Min Act: -0.0001

Data Index: 675789 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.9310. Min Act: -0.0001

Data Index: 938056 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1212171 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.9068. Min Act: -0.0001

Data Index: 175681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.9037. Min Act: -0.0001

Data Index: 61979 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8970. Min Act: -0.0001

Data Index: 198574 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.9007. Min Act: -0.0001

Data Index: 855909 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8940. Min Act: -0.0001

Data Index: 628633 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8778. Min Act: -0.0001

Data Index: 1140044 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8740. Min Act: -0.0001

Data Index: 799457 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8747. Min Act: -0.0001

Data Index: 1295463 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8805. Min Act: -0.0001

Data Index: 631035 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1282622 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8611. Min Act: -0.0001

Data Index: 1001057 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1323772 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8557. Min Act: -0.0001

Data Index: 57681 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8722. Min Act: -0.0001

Data Index: 905031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8665. Min Act: -0.0001

Data Index: 1054357 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8593. Min Act: -0.0001

Data Index: 1060227 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.1447. Min Range: -1.1447

Max Act: 0.8519. Min Act: -0.0001

Data Index: 526325 (C4 (Web Text))

Max Activating Token Index: 151