Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7810. Min Act: -0.0001

Data Index: 534161 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.8272. Min Act: -0.0001

Data Index: 1359701 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.8352. Min Act: -0.0001

Data Index: 770190 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1335450 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7440. Min Act: -0.0001

Data Index: 1280251 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7612. Min Act: -0.0001

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7652. Min Act: -0.0001

Data Index: 1210660 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7625. Min Act: -0.0001

Data Index: 916714 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7460. Min Act: -0.0001

Data Index: 991472 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7846. Min Act: -0.0001

Data Index: 384419 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7259. Min Act: -0.0001

Data Index: 286354 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7228. Min Act: -0.0001

Data Index: 730650 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7862. Min Act: -0.0001

Data Index: 76470 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1019371 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7486. Min Act: -0.0001

Data Index: 533873 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6533. Min Act: -0.0001

Data Index: 81003 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6736. Min Act: -0.0001

Data Index: 845239 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7043. Min Act: -0.0001

Data Index: 900253 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6564. Min Act: -0.0001

Data Index: 316708 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1265354 (C4 (Web Text))

Max Activating Token Index: 867