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

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

Neuron 2993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7816. Min Act: -0.0000

Data Index: 465245 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7921. Min Act: -0.0000

Data Index: 719620 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1218995 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6226. Min Act: -0.0000

Data Index: 872507 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1638 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7186. Min Act: -0.0000

Data Index: 257198 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6855. Min Act: -0.0000

Data Index: 402230 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7089. Min Act: -0.0000

Data Index: 452742 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6981. Min Act: -0.0000

Data Index: 789982 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.7229. Min Act: -0.0000

Data Index: 382245 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6998. Min Act: -0.0000

Data Index: 671089 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1100119 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6885. Min Act: -0.0000

Data Index: 460042 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6376. Min Act: -0.0000

Data Index: 365287 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1132962 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6214. Min Act: -0.0000

Data Index: 505915 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1148960 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.5927. Min Act: -0.0000

Data Index: 245563 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6494. Min Act: -0.0000

Data Index: 972819 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.7921. Min Range: -0.7921

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1202903 (C4 (Web Text))

Max Activating Token Index: 469