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

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

Neuron 1264 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.3128. Min Act: -0.0001

Data Index: 373307 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.1391. Min Act: -0.0002

Data Index: 708597 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.2819. Min Act: -0.0001

Data Index: 708230 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0898. Min Act: -0.0001

Data Index: 1275385 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.1750. Min Act: -0.0001

Data Index: 1149544 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.1376. Min Act: -0.0001

Data Index: 248646 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0730. Min Act: -0.0002

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.1388. Min Act: -0.0001

Data Index: 668486 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0141. Min Act: -0.0001

Data Index: 10637 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0648. Min Act: -0.0001

Data Index: 1146158 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0256. Min Act: -0.0001

Data Index: 207476 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1137037 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0372. Min Act: -0.0001

Data Index: 1344820 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0018. Min Act: -0.0001

Data Index: 877862 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0408. Min Act: -0.0001

Data Index: 980515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0073. Min Act: -0.0001

Data Index: 735617 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9307. Min Act: -0.0001

Data Index: 543138 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 1.3128. Min Range: -1.3128

Max Act: 1.0025. Min Act: -0.0002

Data Index: 145404 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9904. Min Act: -0.0001

Data Index: 244282 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.3128. Min Range: -1.3128

Max Act: 0.9437. Min Act: -0.0001

Data Index: 1265718 (C4 (Web Text))

Max Activating Token Index: 820