Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5328 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.6132. Min Act: -0.0001

Data Index: 840243 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5457. Min Act: -0.0001

Data Index: 782876 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5145. Min Act: -0.0002

Data Index: 1099572 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1054090 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5388. Min Act: -0.0001

Data Index: 123468 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4878. Min Act: -0.0001

Data Index: 888133 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4908. Min Act: -0.0001

Data Index: 532433 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1291193 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4723. Min Act: -0.0001

Data Index: 611527 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4740. Min Act: -0.0001

Data Index: 654743 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4593. Min Act: -0.0001

Data Index: 851326 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4707. Min Act: -0.0001

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4623. Min Act: -0.0001

Data Index: 224429 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.5067. Min Act: -0.0001

Data Index: 951795 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4552. Min Act: -0.0001

Data Index: 95981 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4814. Min Act: -0.0001

Data Index: 662342 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4295. Min Act: -0.0001

Data Index: 770974 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4406. Min Act: -0.0001

Data Index: 852414 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4358. Min Act: -0.0001

Data Index: 352437 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.6132. Min Range: -0.6132

Max Act: 0.4740. Min Act: -0.0001

Data Index: 715539 (C4 (Web Text))

Max Activating Token Index: 323