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

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

Neuron 1633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.4372. Min Act: -0.0001

Data Index: 206503 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1181299 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3914. Min Act: -0.0001

Data Index: 1066208 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3641. Min Act: -0.0001

Data Index: 374934 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3746. Min Act: -0.0001

Data Index: 844481 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3693. Min Act: -0.0001

Data Index: 856735 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3447. Min Act: -0.0000

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3916. Min Act: -0.0001

Data Index: 299751 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3476. Min Act: -0.0001

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.4008. Min Act: -0.0000

Data Index: 759616 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3613. Min Act: -0.0000

Data Index: 235887 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3746. Min Act: -0.0001

Data Index: 696952 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1179162 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3663. Min Act: -0.0001

Data Index: 607753 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3589. Min Act: -0.0001

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3384. Min Act: -0.0001

Data Index: 528332 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3535. Min Act: -0.0000

Data Index: 901983 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1054114 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.4372. Min Range: -0.4372

Max Act: 0.3646. Min Act: -0.0000

Data Index: 592820 (C4 (Web Text))

Max Activating Token Index: 846