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

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

Neuron 2071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1295. Min Range: -1.1295

Max Act: 1.1295. Min Act: -0.0001

Data Index: 54776 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.1295. Min Range: -1.1295

Max Act: 1.0372. Min Act: -0.0001

Data Index: 992725 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.9927. Min Act: -0.0001

Data Index: 359306 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.9131. Min Act: -0.0001

Data Index: 314924 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8879. Min Act: -0.0001

Data Index: 767554 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.9202. Min Act: -0.0001

Data Index: 1133624 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.9092. Min Act: -0.0001

Data Index: 914888 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8812. Min Act: -0.0001

Data Index: 412785 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8556. Min Act: -0.0001

Data Index: 192754 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8757. Min Act: -0.0001

Data Index: 298125 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8412. Min Act: -0.0001

Data Index: 1118873 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8308. Min Act: -0.0001

Data Index: 515832 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8782. Min Act: -0.0001

Data Index: 217830 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1034910 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.7541. Min Act: -0.0001

Data Index: 47251 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8276. Min Act: -0.0001

Data Index: 203458 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8610. Min Act: -0.0001

Data Index: 83633 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.7803. Min Act: -0.0001

Data Index: 603614 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8041. Min Act: -0.0001

Data Index: 1289330 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.1295. Min Range: -1.1295

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1120285 (C4 (Web Text))

Max Activating Token Index: 817