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

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

Neuron 814 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: 1.8466. Min Range: -1.8466

Max Act: 1.8466. Min Act: -0.0001

Data Index: 1053780 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.7938. Min Act: -0.0001

Data Index: 400419 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.4992. Min Act: -0.0001

Data Index: 572873 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6012. Min Act: -0.0001

Data Index: 1133850 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3851. Min Act: -0.0001

Data Index: 684307 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6532. Min Act: -0.0001

Data Index: 1112464 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.4073. Min Act: -0.0001

Data Index: 217484 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3588. Min Act: -0.0001

Data Index: 32846 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3711. Min Act: -0.0001

Data Index: 899631 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.4148. Min Act: -0.0001

Data Index: 194004 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3306. Min Act: -0.0001

Data Index: 767632 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3826. Min Act: -0.0001

Data Index: 1246939 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3400. Min Act: -0.0001

Data Index: 9182 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.2541. Min Act: -0.0001

Data Index: 1037973 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3795. Min Act: -0.0001

Data Index: 694387 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.2257. Min Act: -0.0001

Data Index: 1120329 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3370. Min Act: -0.0001

Data Index: 1063347 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.2658. Min Act: -0.0001

Data Index: 273214 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.3248. Min Act: -0.0001

Data Index: 521994 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.2720. Min Act: -0.0001

Data Index: 1223856 (C4 (Web Text))

Max Activating Token Index: 920