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

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

Neuron 5045 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0624. Min Act: -0.0002

Data Index: 133238 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0586. Min Act: -0.0002

Data Index: 356352 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0564. Min Act: -0.0002

Data Index: 474451 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1389730 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1319661 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1283987 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0002

Data Index: 780813 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0518. Min Act: -0.0002

Data Index: 280250 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1295937 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0647. Min Act: -0.0002

Data Index: 418976 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0556. Min Act: -0.0002

Data Index: 85498 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1050842 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1264987 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0502. Min Act: -0.0002

Data Index: 17670 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1151969 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0461. Min Act: -0.0002

Data Index: 365649 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0499. Min Act: -0.0002

Data Index: 818679 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0486. Min Act: -0.0002

Data Index: 182655 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0485. Min Act: -0.0002

Data Index: 915814 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0501. Min Act: -0.0002

Data Index: 717407 (C4 (Web Text))

Max Activating Token Index: 682