Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1133 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1305098 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0510. Min Act: -0.0002

Data Index: 919268 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1315654 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0518. Min Act: -0.0001

Data Index: 598852 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0503. Min Act: -0.0002

Data Index: 993724 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0524. Min Act: -0.0002

Data Index: 88386 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0500. Min Act: -0.0002

Data Index: 276816 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0489. Min Act: -0.0002

Data Index: 917374 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0478. Min Act: -0.0001

Data Index: 596355 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0473. Min Act: -0.0002

Data Index: 163052 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1017722 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0480. Min Act: -0.0002

Data Index: 813489 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0455. Min Act: -0.0002

Data Index: 305079 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0453. Min Act: -0.0002

Data Index: 804914 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0454. Min Act: -0.0001

Data Index: 856884 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0468. Min Act: -0.0002

Data Index: 937770 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0449. Min Act: -0.0002

Data Index: 894786 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1394580 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0442. Min Act: -0.0002

Data Index: 577339 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0439. Min Act: -0.0001

Data Index: 479591 (C4 (Web Text))

Max Activating Token Index: 441