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

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

Neuron 517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1634474 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6049. Min Act: -0.0001

Data Index: 1426219 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6443. Min Act: -0.0001

Data Index: 1483277 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5526. Min Act: -0.0001

Data Index: 1552261 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1495788 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5925. Min Act: -0.0001

Data Index: 1406789 (Python Code)

Max Activating Token Index: 753

Text #6

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5556. Min Act: -0.0001

Data Index: 1426099 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6066. Min Act: -0.0001

Data Index: 1379295 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5854. Min Act: -0.0001

Data Index: 938817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1456231 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5275. Min Act: -0.0001

Data Index: 215322 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5490. Min Act: -0.0001

Data Index: 1530779 (Python Code)

Max Activating Token Index: 866

Text #12

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1611762 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5705. Min Act: -0.0001

Data Index: 1619457 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5152. Min Act: -0.0002

Data Index: 196531 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4612. Min Act: -0.0002

Data Index: 5456 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5433. Min Act: -0.0001

Data Index: 1528966 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1435708 (Python Code)

Max Activating Token Index: 620

Text #18

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1566233 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1405602 (Python Code)

Max Activating Token Index: 868