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

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

Neuron 1975 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: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 898891 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0532. Min Act: -0.0003

Data Index: 55528 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1282421 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0545. Min Act: -0.0003

Data Index: 893962 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0474. Min Act: -0.0003

Data Index: 476496 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0543. Min Act: -0.0003

Data Index: 521688 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0510. Min Act: -0.0003

Data Index: 787663 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0535. Min Act: -0.0003

Data Index: 388847 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0531. Min Act: -0.0003

Data Index: 238941 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0512. Min Act: -0.0003

Data Index: 873966 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0496. Min Act: -0.0003

Data Index: 142008 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0494. Min Act: -0.0003

Data Index: 497393 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0498. Min Act: -0.0003

Data Index: 586479 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0505. Min Act: -0.0003

Data Index: 633014 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0481. Min Act: -0.0003

Data Index: 594594 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1134485 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0488. Min Act: -0.0003

Data Index: 243271 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1100595 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0485. Min Act: -0.0003

Data Index: 187206 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0474. Min Act: -0.0003

Data Index: 176005 (C4 (Web Text))

Max Activating Token Index: 288