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

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

Neuron 1600 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: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0002

Data Index: 344158 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0785. Min Act: -0.0002

Data Index: 448019 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0766. Min Act: -0.0002

Data Index: 940946 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0722. Min Act: -0.0001

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1336113 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1068464 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0607. Min Act: -0.0001

Data Index: 699770 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0635. Min Act: -0.0001

Data Index: 491256 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0571. Min Act: -0.0002

Data Index: 650578 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0536. Min Act: -0.0001

Data Index: 44210 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0517. Min Act: -0.0002

Data Index: 964302 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0587. Min Act: -0.0001

Data Index: 526459 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0613. Min Act: -0.0002

Data Index: 348859 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0588. Min Act: -0.0001

Data Index: 139735 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0507. Min Act: -0.0001

Data Index: 901064 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1107792 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0505. Min Act: -0.0002

Data Index: 597504 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0497. Min Act: -0.0001

Data Index: 292374 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1254348 (C4 (Web Text))

Max Activating Token Index: 636