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

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

Neuron 3485 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: 1.6760. Min Range: -1.6760

Max Act: 1.6760. Min Act: -0.0001

Data Index: 274545 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.4751. Min Act: -0.0001

Data Index: 798763 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.1120. Min Act: -0.0001

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.0943. Min Act: -0.0001

Data Index: 881372 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.4036. Min Act: -0.0001

Data Index: 500950 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.0995. Min Act: -0.0001

Data Index: 417024 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.1141. Min Act: -0.0001

Data Index: 261125 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.0340. Min Act: -0.0001

Data Index: 538734 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.6760. Min Range: -1.6760

Max Act: 1.0714. Min Act: -0.0001

Data Index: 1274236 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.9617. Min Act: -0.0001

Data Index: 1012739 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.8388. Min Act: -0.0001

Data Index: 10500 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.9716. Min Act: -0.0001

Data Index: 794385 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.9340. Min Act: -0.0001

Data Index: 535942 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.9118. Min Act: -0.0001

Data Index: 697743 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.8644. Min Act: -0.0001

Data Index: 866171 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.8536. Min Act: -0.0001

Data Index: 1148733 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.8955. Min Act: -0.0001

Data Index: 584256 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.8022. Min Act: -0.0001

Data Index: 1022019 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.9134. Min Act: -0.0001

Data Index: 986074 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.6760. Min Range: -1.6760

Max Act: 0.9173. Min Act: -0.0001

Data Index: 1152199 (C4 (Web Text))

Max Activating Token Index: 224