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

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

Neuron 3640 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: 0.1103. Min Range: -0.1103

Max Act: 0.1103. Min Act: -0.0001

Data Index: 42238 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0848. Min Act: -0.0001

Data Index: 379941 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1185735 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0759. Min Act: -0.0001

Data Index: 369863 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0737. Min Act: -0.0001

Data Index: 303050 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0729. Min Act: -0.0001

Data Index: 498917 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0721. Min Act: -0.0001

Data Index: 516147 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0710. Min Act: -0.0001

Data Index: 982291 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1041994 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0722. Min Act: -0.0001

Data Index: 628729 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0690. Min Act: -0.0001

Data Index: 276175 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0690. Min Act: -0.0001

Data Index: 521853 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1056835 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0696. Min Act: -0.0001

Data Index: 907638 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0665. Min Act: -0.0002

Data Index: 151063 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0664. Min Act: -0.0001

Data Index: 353639 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0652. Min Act: -0.0001

Data Index: 514841 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0654. Min Act: -0.0001

Data Index: 725496 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0649. Min Act: -0.0001

Data Index: 711433 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0659. Min Act: -0.0001

Data Index: 9202 (C4 (Web Text))

Max Activating Token Index: 73