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

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

Neuron 2499 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1048611 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1511852 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1097671 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1042104 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1512668 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0616. Min Act: -0.0001

Data Index: 150511 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0531. Min Act: -0.0001

Data Index: 802782 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0542. Min Act: -0.0001

Data Index: 532623 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0532. Min Act: -0.0001

Data Index: 533286 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0496. Min Act: -0.0001

Data Index: 889023 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1191182 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0468. Min Act: -0.0001

Data Index: 166075 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1313915 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1648550 (Python Code)

Max Activating Token Index: 912

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1128459 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0521. Min Act: -0.0001

Data Index: 928568 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0472. Min Act: -0.0001

Data Index: 660269 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1058918 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0520. Min Act: -0.0001

Data Index: 24493 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0445. Min Act: -0.0001

Data Index: 907907 (C4 (Web Text))

Max Activating Token Index: 243