Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5524. Min Act: -0.0000

Data Index: 700916 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1599756 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1572318 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3876. Min Act: -0.0000

Data Index: 29785 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4162. Min Act: -0.0000

Data Index: 59091 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1555560 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1404224 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4165. Min Act: -0.0000

Data Index: 839897 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1514466 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4405. Min Act: -0.0000

Data Index: 959011 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1612833 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1543912 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4027. Min Act: -0.0000

Data Index: 899804 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1598424 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1370286 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3901. Min Act: -0.0000

Data Index: 371899 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1517523 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1089125 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4067. Min Act: -0.0000

Data Index: 945345 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1051412 (C4 (Web Text))

Max Activating Token Index: 1017