Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2110 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0001

Data Index: 742777 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0609. Min Act: -0.0001

Data Index: 52072 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0600. Min Act: -0.0001

Data Index: 227199 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0595. Min Act: -0.0001

Data Index: 321516 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0549. Min Act: -0.0001

Data Index: 266228 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1332045 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0537. Min Act: -0.0001

Data Index: 688835 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0559. Min Act: -0.0001

Data Index: 821052 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0560. Min Act: -0.0001

Data Index: 702670 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0552. Min Act: -0.0001

Data Index: 417212 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1256118 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1244867 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1075033 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0530. Min Act: -0.0001

Data Index: 630062 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0527. Min Act: -0.0001

Data Index: 823829 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0491. Min Act: -0.0001

Data Index: 22825 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1395435 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1143644 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1070784 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0511. Min Act: -0.0001

Data Index: 739501 (C4 (Web Text))

Max Activating Token Index: 228