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

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

Neuron 3490 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1487. Min Range: -4.1487

Max Act: 4.1487. Min Act: -0.0001

Data Index: 734735 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 4.1487. Min Range: -4.1487

Max Act: 3.0985. Min Act: -0.0001

Data Index: 991369 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.7244. Min Act: -0.0001

Data Index: 1290110 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.4524. Min Act: -0.0001

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 4.1487. Min Range: -4.1487

Max Act: 3.1133. Min Act: -0.0001

Data Index: 1132080 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.3581. Min Act: -0.0001

Data Index: 447101 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.4910. Min Act: -0.0001

Data Index: 730974 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.5575. Min Act: -0.0001

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.3017. Min Act: -0.0001

Data Index: 637014 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.1952. Min Act: -0.0001

Data Index: 947952 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.1311. Min Act: -0.0001

Data Index: 1249278 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.1392. Min Act: -0.0001

Data Index: 1314309 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.1352. Min Act: -0.0001

Data Index: 699629 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.1548. Min Act: -0.0001

Data Index: 369084 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.0423. Min Act: -0.0001

Data Index: 740848 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.1606. Min Act: -0.0001

Data Index: 780129 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 4.1487. Min Range: -4.1487

Max Act: 2.0063. Min Act: -0.0001

Data Index: 891022 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 4.1487. Min Range: -4.1487

Max Act: 1.9907. Min Act: -0.0001

Data Index: 956099 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 4.1487. Min Range: -4.1487

Max Act: 1.9621. Min Act: -0.0001

Data Index: 1326462 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 4.1487. Min Range: -4.1487

Max Act: 1.8180. Min Act: -0.0001

Data Index: 259711 (C4 (Web Text))

Max Activating Token Index: 522