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

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

Neuron 1863 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0001

Data Index: 844250 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1144. Min Act: -0.0001

Data Index: 872538 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1310176 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0980. Min Act: -0.0001

Data Index: 449813 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0909. Min Act: -0.0001

Data Index: 133689 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0883. Min Act: -0.0001

Data Index: 703208 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0788. Min Act: -0.0001

Data Index: 528598 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0900. Min Act: -0.0001

Data Index: 430215 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0861. Min Act: -0.0001

Data Index: 607064 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0796. Min Act: -0.0001

Data Index: 695481 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0858. Min Act: -0.0001

Data Index: 208813 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0799. Min Act: -0.0001

Data Index: 252044 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0788. Min Act: -0.0001

Data Index: 256972 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0801. Min Act: -0.0001

Data Index: 647938 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0737. Min Act: -0.0001

Data Index: 103948 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0732. Min Act: -0.0001

Data Index: 639734 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1294054 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0762. Min Act: -0.0001

Data Index: 935968 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1211588 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0746. Min Act: -0.0001

Data Index: 465819 (C4 (Web Text))

Max Activating Token Index: 174