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

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

Neuron 2013 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: 0.4505. Min Range: -0.4505

Max Act: 0.4505. Min Act: -0.0001

Data Index: 634335 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4134. Min Act: -0.0000

Data Index: 6321 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4248. Min Act: -0.0001

Data Index: 605288 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1357452 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4032. Min Act: -0.0000

Data Index: 780842 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4040. Min Act: -0.0000

Data Index: 970388 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3981. Min Act: -0.0000

Data Index: 621632 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3856. Min Act: -0.0001

Data Index: 588504 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3850. Min Act: -0.0000

Data Index: 842220 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3658. Min Act: -0.0000

Data Index: 442586 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3819. Min Act: -0.0001

Data Index: 578639 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3776. Min Act: -0.0000

Data Index: 533430 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1194519 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3919. Min Act: -0.0000

Data Index: 459648 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1174959 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3476. Min Act: -0.0000

Data Index: 441076 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1852 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3599. Min Act: -0.0001

Data Index: 1343174 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3505. Min Act: -0.0000

Data Index: 991503 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3566. Min Act: -0.0001

Data Index: 303852 (C4 (Web Text))

Max Activating Token Index: 431