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

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

Neuron 1362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.7787. Min Act: -0.0001

Data Index: 1133657 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.9736. Min Act: -0.0001

Data Index: 335929 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.8733. Min Act: -0.0001

Data Index: 228691 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.7278. Min Act: -0.0001

Data Index: 609453 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.6271. Min Act: -0.0001

Data Index: 764377 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.5674. Min Act: -0.0001

Data Index: 595411 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.6551. Min Act: -0.0001

Data Index: 1130823 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.5770. Min Act: -0.0001

Data Index: 524439 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.6039. Min Act: -0.0001

Data Index: 1168610 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4970. Min Act: -0.0001

Data Index: 1266414 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.6126. Min Act: -0.0001

Data Index: 448160 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.5093. Min Act: -0.0001

Data Index: 390135 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4898. Min Act: -0.0001

Data Index: 1300645 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4271. Min Act: -0.0001

Data Index: 990178 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4077. Min Act: -0.0001

Data Index: 322353 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4473. Min Act: -0.0001

Data Index: 209892 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4823. Min Act: -0.0001

Data Index: 679833 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.3511. Min Act: -0.0001

Data Index: 367213 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4326. Min Act: -0.0001

Data Index: 1165203 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.9736. Min Range: -1.9736

Max Act: 1.4834. Min Act: -0.0001

Data Index: 671250 (C4 (Web Text))

Max Activating Token Index: 955