Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 983 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1297844 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0516. Min Act: -0.0003

Data Index: 182623 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0540. Min Act: -0.0003

Data Index: 482480 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1137540 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0512. Min Act: -0.0003

Data Index: 630868 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0507. Min Act: -0.0002

Data Index: 351231 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0495. Min Act: -0.0003

Data Index: 969887 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0491. Min Act: -0.0003

Data Index: 551690 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1254241 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1105564 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0478. Min Act: -0.0003

Data Index: 591627 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0491. Min Act: -0.0003

Data Index: 374589 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0484. Min Act: -0.0002

Data Index: 136590 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0480. Min Act: -0.0003

Data Index: 303522 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0488. Min Act: -0.0003

Data Index: 845585 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0478. Min Act: -0.0003

Data Index: 30980 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1343162 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0487. Min Act: -0.0003

Data Index: 915583 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0478. Min Act: -0.0003

Data Index: 520646 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0467. Min Act: -0.0003

Data Index: 268051 (C4 (Web Text))

Max Activating Token Index: 225