Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 628 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0609. Min Act: -0.0001

Data Index: 261703 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0001

Data Index: 890823 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0591. Min Act: -0.0001

Data Index: 409319 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0575. Min Act: -0.0001

Data Index: 666517 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0517. Min Act: -0.0001

Data Index: 902843 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0519. Min Act: -0.0001

Data Index: 606764 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1286151 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0583. Min Act: -0.0001

Data Index: 970604 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1079522 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0555. Min Act: -0.0001

Data Index: 519728 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1002560 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0428. Min Act: -0.0001

Data Index: 856763 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0512. Min Act: -0.0001

Data Index: 610955 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1177287 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1356068 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1057143 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0549. Min Act: -0.0001

Data Index: 94477 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0516. Min Act: -0.0001

Data Index: 813216 (C4 (Web Text))

Max Activating Token Index: 136