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

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

Neuron 45 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: 0.0787. Min Range: -0.0787

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1163648 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0764. Min Act: -0.0003

Data Index: 213317 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1327134 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0759. Min Act: -0.0003

Data Index: 268087 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0692. Min Act: -0.0003

Data Index: 221495 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0632. Min Act: -0.0003

Data Index: 113316 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0617. Min Act: -0.0003

Data Index: 432697 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1319436 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0642. Min Act: -0.0003

Data Index: 405286 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0646. Min Act: -0.0003

Data Index: 292221 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0619. Min Act: -0.0003

Data Index: 714832 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0629. Min Act: -0.0003

Data Index: 172773 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0645. Min Act: -0.0003

Data Index: 628404 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0646. Min Act: -0.0003

Data Index: 846893 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0651. Min Act: -0.0003

Data Index: 248392 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0629. Min Act: -0.0003

Data Index: 253145 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0583. Min Act: -0.0003

Data Index: 277417 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1307186 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1004614 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0597. Min Act: -0.0003

Data Index: 133181 (C4 (Web Text))

Max Activating Token Index: 376