Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 116 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0003

Data Index: 269890 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0883. Min Act: -0.0003

Data Index: 148280 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0705. Min Act: -0.0003

Data Index: 219539 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0719. Min Act: -0.0003

Data Index: 34719 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0723. Min Act: -0.0003

Data Index: 590439 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0668. Min Act: -0.0003

Data Index: 894025 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0626. Min Act: -0.0003

Data Index: 469654 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1092423 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1085297 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0608. Min Act: -0.0003

Data Index: 166584 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1156427 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0617. Min Act: -0.0003

Data Index: 268190 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0587. Min Act: -0.0003

Data Index: 677131 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1145323 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0562. Min Act: -0.0003

Data Index: 719217 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0573. Min Act: -0.0003

Data Index: 544553 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0545. Min Act: -0.0003

Data Index: 983122 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0555. Min Act: -0.0003

Data Index: 178081 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0542. Min Act: -0.0003

Data Index: 322575 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0555. Min Act: -0.0003

Data Index: 806058 (C4 (Web Text))

Max Activating Token Index: 258