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

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

Neuron 2383 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.9271. Min Act: -0.0000

Data Index: 1214543 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.9047. Min Act: -0.0000

Data Index: 927630 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7513. Min Act: -0.0000

Data Index: 1184034 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8444. Min Act: -0.0000

Data Index: 965466 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1351652 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7957. Min Act: -0.0000

Data Index: 139461 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1259473 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7807. Min Act: -0.0000

Data Index: 542545 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.6609. Min Act: -0.0000

Data Index: 422659 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.6554. Min Act: -0.0000

Data Index: 967367 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.5478. Min Act: -0.0000

Data Index: 783085 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1341256 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.6341. Min Act: -0.0000

Data Index: 940471 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7144. Min Act: -0.0000

Data Index: 840085 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.5336. Min Act: -0.0000

Data Index: 644559 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7136. Min Act: -0.0000

Data Index: 891211 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.6175. Min Act: -0.0000

Data Index: 1190087 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.5279. Min Act: -0.0000

Data Index: 905753 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7055. Min Act: -0.0000

Data Index: 87952 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1064867 (C4 (Web Text))

Max Activating Token Index: 833