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

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

Neuron 3639 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.9276. Min Act: -0.0001

Data Index: 279434 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.9428. Min Act: -0.0001

Data Index: 196607 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7435. Min Act: -0.0000

Data Index: 475522 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6544. Min Act: -0.0001

Data Index: 762650 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7135. Min Act: -0.0001

Data Index: 421052 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7651. Min Act: -0.0000

Data Index: 940852 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6855. Min Act: -0.0001

Data Index: 172913 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5371. Min Act: -0.0001

Data Index: 433424 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1083985 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6971. Min Act: -0.0001

Data Index: 423375 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1169917 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6520. Min Act: -0.0001

Data Index: 129568 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6404. Min Act: -0.0001

Data Index: 837516 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6491. Min Act: -0.0000

Data Index: 744647 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1154009 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5721. Min Act: -0.0000

Data Index: 522806 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5704. Min Act: -0.0001

Data Index: 601397 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6449. Min Act: -0.0001

Data Index: 1283296 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5271. Min Act: -0.0000

Data Index: 973096 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5350. Min Act: -0.0001

Data Index: 573004 (C4 (Web Text))

Max Activating Token Index: 696