Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0001

Data Index: 384411 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1120750 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1723. Min Act: -0.0001

Data Index: 822448 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1707. Min Act: 0.0001

Data Index: 1141712 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1635. Min Act: -0.0000

Data Index: 43620 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1701. Min Act: 0.0000

Data Index: 1117407 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1611. Min Act: -0.0001

Data Index: 17535 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1722. Min Act: -0.0001

Data Index: 526041 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1625. Min Act: -0.0000

Data Index: 964913 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1604. Min Act: -0.0001

Data Index: 466705 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1517. Min Act: -0.0001

Data Index: 302869 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1305416 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1567. Min Act: -0.0000

Data Index: 891203 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1223057 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1441. Min Act: -0.0001

Data Index: 881647 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1489. Min Act: -0.0001

Data Index: 803471 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1491. Min Act: -0.0001

Data Index: 67882 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1521. Min Act: 0.0005

Data Index: 63845 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1474. Min Act: -0.0001

Data Index: 820320 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1420. Min Act: -0.0001

Data Index: 710628 (C4 (Web Text))

Max Activating Token Index: 593