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

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

Neuron 4233 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: 3.2772. Min Range: -3.2772

Max Act: 3.2772. Min Act: -0.0001

Data Index: 88882 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 3.2772. Min Range: -3.2772

Max Act: 3.2084. Min Act: -0.0000

Data Index: 1197482 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 3.2772. Min Range: -3.2772

Max Act: 3.1740. Min Act: -0.0000

Data Index: 1317742 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.2772. Min Range: -3.2772

Max Act: 3.0833. Min Act: -0.0000

Data Index: 833352 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 3.2772. Min Range: -3.2772

Max Act: 3.0123. Min Act: -0.0001

Data Index: 1148030 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.9508. Min Act: -0.0001

Data Index: 477909 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.9567. Min Act: -0.0001

Data Index: 639708 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 3.2772. Min Range: -3.2772

Max Act: 3.0750. Min Act: -0.0001

Data Index: 549076 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.9406. Min Act: -0.0001

Data Index: 1174493 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.9215. Min Act: -0.0001

Data Index: 1151014 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.7263. Min Act: -0.0001

Data Index: 359490 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.7363. Min Act: -0.0001

Data Index: 142656 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.7213. Min Act: -0.0000

Data Index: 773166 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.8634. Min Act: -0.0001

Data Index: 1004058 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.5833. Min Act: -0.0001

Data Index: 305227 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.9283. Min Act: -0.0001

Data Index: 24769 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.6066. Min Act: -0.0001

Data Index: 700075 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.6822. Min Act: -0.0000

Data Index: 1312197 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.6510. Min Act: -0.0001

Data Index: 701554 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 3.2772. Min Range: -3.2772

Max Act: 2.8046. Min Act: -0.0001

Data Index: 161099 (C4 (Web Text))

Max Activating Token Index: 332