Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 576 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0001

Data Index: 596727 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0694. Min Act: -0.0000

Data Index: 326511 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0670. Min Act: -0.0000

Data Index: 247370 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0696. Min Act: -0.0001

Data Index: 925947 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1256435 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0633. Min Act: -0.0000

Data Index: 100540 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0653. Min Act: -0.0000

Data Index: 881366 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0645. Min Act: -0.0000

Data Index: 421627 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0643. Min Act: -0.0000

Data Index: 443365 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0647. Min Act: -0.0000

Data Index: 239661 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0639. Min Act: -0.0000

Data Index: 737953 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0633. Min Act: -0.0000

Data Index: 305538 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0604. Min Act: -0.0000

Data Index: 558633 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0648. Min Act: -0.0000

Data Index: 58028 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1304980 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0585. Min Act: -0.0000

Data Index: 739506 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0565. Min Act: -0.0000

Data Index: 519562 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0580. Min Act: -0.0000

Data Index: 891732 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1007255 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0567. Min Act: -0.0000

Data Index: 825337 (C4 (Web Text))

Max Activating Token Index: 865