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

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

Neuron 455 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: 0.7663. Min Range: -0.7663

Max Act: 0.7663. Min Act: -0.0003

Data Index: 556424 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.7549. Min Act: -0.0003

Data Index: 1095734 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.7277. Min Act: -0.0003

Data Index: 616508 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.7234. Min Act: -0.0003

Data Index: 1313508 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6722. Min Act: -0.0003

Data Index: 367404 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6905. Min Act: -0.0003

Data Index: 966513 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6788. Min Act: -0.0003

Data Index: 1158963 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6732. Min Act: -0.0003

Data Index: 1070731 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6626. Min Act: -0.0003

Data Index: 184636 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6400. Min Act: -0.0003

Data Index: 1200529 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6371. Min Act: -0.0003

Data Index: 77534 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6331. Min Act: -0.0003

Data Index: 290452 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6105. Min Act: -0.0003

Data Index: 748118 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6676. Min Act: -0.0003

Data Index: 695756 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6249. Min Act: -0.0003

Data Index: 489851 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6400. Min Act: -0.0003

Data Index: 1238707 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.5835. Min Act: -0.0003

Data Index: 1180336 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.5961. Min Act: -0.0003

Data Index: 1271138 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6371. Min Act: -0.0003

Data Index: 1111495 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.7663. Min Range: -0.7663

Max Act: 0.6298. Min Act: -0.0003

Data Index: 256185 (C4 (Web Text))

Max Activating Token Index: 778