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

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

Neuron 2070 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: 0.8738. Min Range: -0.8738

Max Act: 0.8738. Min Act: -0.0001

Data Index: 1091889 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8406. Min Act: -0.0001

Data Index: 155207 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7582. Min Act: -0.0001

Data Index: 288987 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7763. Min Act: -0.0001

Data Index: 212669 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7156. Min Act: -0.0001

Data Index: 782746 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7378. Min Act: -0.0001

Data Index: 528277 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7125. Min Act: -0.0001

Data Index: 780887 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1357420 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7119. Min Act: -0.0001

Data Index: 58950 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8246. Min Act: -0.0001

Data Index: 595815 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7460. Min Act: -0.0001

Data Index: 74455 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6700. Min Act: -0.0001

Data Index: 240092 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7119. Min Act: -0.0001

Data Index: 876944 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7031. Min Act: -0.0001

Data Index: 742763 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7045. Min Act: -0.0001

Data Index: 941426 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6780. Min Act: -0.0001

Data Index: 698688 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6772. Min Act: -0.0001

Data Index: 351471 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6964. Min Act: -0.0001

Data Index: 786895 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6969. Min Act: -0.0001

Data Index: 1188486 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7187. Min Act: -0.0001

Data Index: 725226 (C4 (Web Text))

Max Activating Token Index: 670