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

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

Neuron 1232 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0973. Min Act: -0.0000

Data Index: 941217 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1273610 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: 0.0000

Data Index: 1014724 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0169. Min Act: -0.0000

Data Index: 16313 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1193945 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9989. Min Act: -0.0000

Data Index: 44140 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9158. Min Act: -0.0000

Data Index: 285534 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9841. Min Act: -0.0000

Data Index: 834604 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1358806 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9453. Min Act: 0.0000

Data Index: 642343 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9221. Min Act: -0.0000

Data Index: 495714 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9242. Min Act: -0.0000

Data Index: 402500 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1072357 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8617. Min Act: -0.0000

Data Index: 818483 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8723. Min Act: -0.0000

Data Index: 385064 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8845. Min Act: -0.0000

Data Index: 570576 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8840. Min Act: -0.0000

Data Index: 510946 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1077958 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8732. Min Act: 0.0000

Data Index: 1083552 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8766. Min Act: 0.0000

Data Index: 1236606 (C4 (Web Text))

Max Activating Token Index: 928