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

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

Neuron 3265 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0003

Data Index: 646229 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0761. Min Act: -0.0003

Data Index: 706521 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1134540 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0620. Min Act: -0.0002

Data Index: 392621 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1277594 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0597. Min Act: -0.0002

Data Index: 827804 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0594. Min Act: -0.0003

Data Index: 899250 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0569. Min Act: -0.0003

Data Index: 198429 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0554. Min Act: -0.0003

Data Index: 368551 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0543. Min Act: -0.0002

Data Index: 608867 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0529. Min Act: -0.0003

Data Index: 382272 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0528. Min Act: -0.0002

Data Index: 853546 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0513. Min Act: -0.0003

Data Index: 338858 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0512. Min Act: -0.0003

Data Index: 802494 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0502. Min Act: -0.0002

Data Index: 428215 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0480. Min Act: -0.0002

Data Index: 878588 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0466. Min Act: -0.0003

Data Index: 798048 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1146623 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1220969 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0459. Min Act: -0.0003

Data Index: 332976 (C4 (Web Text))

Max Activating Token Index: 284