Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1186 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0702. Min Act: -0.0003

Data Index: 124950 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0700. Min Act: -0.0003

Data Index: 602434 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0003

Data Index: 228096 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1033371 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1122055 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0628. Min Act: -0.0003

Data Index: 307907 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1030133 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0723. Min Act: -0.0003

Data Index: 809588 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0589. Min Act: -0.0003

Data Index: 59882 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0670. Min Act: -0.0003

Data Index: 167746 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0643. Min Act: -0.0003

Data Index: 916946 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0658. Min Act: -0.0003

Data Index: 297820 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0657. Min Act: -0.0003

Data Index: 772917 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1264077 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0663. Min Act: -0.0003

Data Index: 549648 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1601247 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0620. Min Act: -0.0003

Data Index: 268914 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0627. Min Act: -0.0003

Data Index: 860811 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0643. Min Act: -0.0003

Data Index: 65362 (C4 (Web Text))

Max Activating Token Index: 502