Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 66 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1190202 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6299. Min Act: -0.0000

Data Index: 283488 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4833. Min Act: -0.0001

Data Index: 549555 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4852. Min Act: -0.0001

Data Index: 1134616 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4773. Min Act: -0.0001

Data Index: 392360 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1353182 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4849. Min Act: -0.0000

Data Index: 554247 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1278736 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4522. Min Act: -0.0000

Data Index: 123699 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1005161 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4701. Min Act: -0.0001

Data Index: 157766 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4633. Min Act: -0.0001

Data Index: 791214 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4605. Min Act: -0.0000

Data Index: 812916 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4498. Min Act: -0.0000

Data Index: 290263 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4204. Min Act: -0.0001

Data Index: 71805 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4087. Min Act: -0.0001

Data Index: 680623 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4067. Min Act: -0.0001

Data Index: 1151242 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1020165 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4551. Min Act: -0.0000

Data Index: 793793 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.4041. Min Act: -0.0000

Data Index: 923022 (C4 (Web Text))

Max Activating Token Index: 853