Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1153 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.5042. Min Act: -0.0001

Data Index: 806695 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4932. Min Act: -0.0001

Data Index: 213912 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1204539 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4706. Min Act: -0.0001

Data Index: 203891 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4459. Min Act: -0.0001

Data Index: 493773 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4396. Min Act: -0.0001

Data Index: 889869 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4043. Min Act: -0.0001

Data Index: 75958 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1067484 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4217. Min Act: -0.0001

Data Index: 757967 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3958. Min Act: -0.0001

Data Index: 1042850 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1358427 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3580. Min Act: -0.0001

Data Index: 436097 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1195613 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3680. Min Act: -0.0001

Data Index: 747722 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3381. Min Act: -0.0001

Data Index: 594456 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3607. Min Act: -0.0001

Data Index: 143958 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.4112. Min Act: -0.0001

Data Index: 138964 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3838. Min Act: -0.0001

Data Index: 1283092 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3934. Min Act: -0.0001

Data Index: 859485 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.5042. Min Range: -0.5042

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1055894 (C4 (Web Text))

Max Activating Token Index: 696