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

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

Neuron 2544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.7543. Min Act: -0.0001

Data Index: 136827 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.5444. Min Act: -0.0002

Data Index: 587058 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.4454. Min Act: -0.0002

Data Index: 1035171 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.3530. Min Act: -0.0002

Data Index: 116667 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.1432. Min Act: -0.0001

Data Index: 457209 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.1323. Min Act: -0.0002

Data Index: 715141 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.2214. Min Act: -0.0001

Data Index: 1325261 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.2116. Min Act: -0.0001

Data Index: 800755 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.0898. Min Act: -0.0002

Data Index: 817249 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.1690. Min Act: -0.0002

Data Index: 1234879 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.1272. Min Act: -0.0001

Data Index: 187592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.7543. Min Range: -1.7543

Max Act: 1.0657. Min Act: -0.0002

Data Index: 303178 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9894. Min Act: -0.0002

Data Index: 267008 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9791. Min Act: -0.0002

Data Index: 1007179 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9888. Min Act: -0.0002

Data Index: 720493 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9505. Min Act: -0.0001

Data Index: 521154 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9242. Min Act: -0.0002

Data Index: 508522 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9772. Min Act: -0.0002

Data Index: 558403 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9447. Min Act: -0.0001

Data Index: 1205717 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.7543. Min Range: -1.7543

Max Act: 0.9135. Min Act: -0.0001

Data Index: 465044 (C4 (Web Text))

Max Activating Token Index: 277