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

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

Neuron 5029 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: 0.1585. Min Range: -0.1585

Max Act: 0.1585. Min Act: -0.0001

Data Index: 828859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.1406. Min Act: -0.0002

Data Index: 955113 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0777. Min Act: -0.0001

Data Index: 313513 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1079111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0568. Min Act: -0.0001

Data Index: 878694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1106599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0508. Min Act: -0.0001

Data Index: 970951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1110860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0514. Min Act: -0.0001

Data Index: 675788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0513. Min Act: -0.0001

Data Index: 51873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0456. Min Act: -0.0001

Data Index: 710983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1047452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0441. Min Act: -0.0001

Data Index: 271991 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0445. Min Act: -0.0001

Data Index: 966656 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1092078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0426. Min Act: -0.0001

Data Index: 196144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0432. Min Act: -0.0001

Data Index: 267067 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0433. Min Act: -0.0001

Data Index: 620842 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0430. Min Act: -0.0001

Data Index: 756593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1585. Min Range: -0.1585

Max Act: 0.0420. Min Act: -0.0001

Data Index: 904146 (C4 (Web Text))

Max Activating Token Index: 1023