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

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

Neuron 4065 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.8713. Min Act: -0.0001

Data Index: 211325 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 3.1273. Min Range: -3.1273

Max Act: 3.1273. Min Act: -0.0001

Data Index: 531036 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7065. Min Act: -0.0001

Data Index: 566913 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6855. Min Act: -0.0001

Data Index: 1096036 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7969. Min Act: -0.0001

Data Index: 632695 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.5705. Min Act: -0.0001

Data Index: 1197228 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6247. Min Act: -0.0001

Data Index: 1048876 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 3.1273. Min Range: -3.1273

Max Act: 3.0523. Min Act: -0.0001

Data Index: 371262 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6389. Min Act: -0.0001

Data Index: 224617 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.5105. Min Act: -0.0001

Data Index: 765796 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7283. Min Act: -0.0001

Data Index: 849924 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7122. Min Act: -0.0001

Data Index: 1347486 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.5503. Min Act: -0.0001

Data Index: 191877 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.2915. Min Act: -0.0001

Data Index: 60603 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.3892. Min Act: -0.0001

Data Index: 1198489 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.6484. Min Act: -0.0001

Data Index: 475804 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.5233. Min Act: -0.0001

Data Index: 1327139 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.7025. Min Act: -0.0001

Data Index: 1209333 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.4524. Min Act: -0.0001

Data Index: 633317 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.1273. Min Range: -3.1273

Max Act: 2.5732. Min Act: -0.0001

Data Index: 779034 (C4 (Web Text))

Max Activating Token Index: 1003