Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0003

Data Index: 564132 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0833. Min Act: -0.0003

Data Index: 698843 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0841. Min Act: -0.0003

Data Index: 904361 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1183262 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0784. Min Act: -0.0003

Data Index: 35085 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0800. Min Act: -0.0003

Data Index: 362553 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1210474 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0775. Min Act: -0.0004

Data Index: 71349 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1294514 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1033035 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0743. Min Act: -0.0004

Data Index: 236529 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1270584 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0756. Min Act: -0.0003

Data Index: 56370 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1300245 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1119756 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0700. Min Act: -0.0004

Data Index: 1214495 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0701. Min Act: -0.0003

Data Index: 726304 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0735. Min Act: -0.0003

Data Index: 584419 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0708. Min Act: -0.0004

Data Index: 687247 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0680. Min Act: -0.0003

Data Index: 802156 (C4 (Web Text))

Max Activating Token Index: 403