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

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

Neuron 2592 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: 3.0725. Min Range: -3.0725

Max Act: 3.0725. Min Act: -0.0000

Data Index: 379516 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.9466. Min Act: -0.0000

Data Index: 878129 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.6478. Min Act: -0.0000

Data Index: 478872 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.6093. Min Act: -0.0000

Data Index: 161984 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.6081. Min Act: -0.0000

Data Index: 460941 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.6392. Min Act: -0.0000

Data Index: 795366 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.5362. Min Act: -0.0000

Data Index: 189440 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.3804. Min Act: -0.0000

Data Index: 1246925 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.1238. Min Act: -0.0000

Data Index: 1142135 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.4391. Min Act: -0.0000

Data Index: 105833 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.1617. Min Act: -0.0000

Data Index: 645806 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.8707. Min Act: -0.0000

Data Index: 1305466 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.1102. Min Act: -0.0000

Data Index: 686442 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.2617. Min Act: -0.0000

Data Index: 1284910 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 3.0725. Min Range: -3.0725

Max Act: 1.9565. Min Act: -0.0000

Data Index: 226232 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.3722. Min Act: -0.0000

Data Index: 944004 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.1118. Min Act: -0.0000

Data Index: 508988 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.0475. Min Act: -0.0000

Data Index: 274555 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.2277. Min Act: -0.0000

Data Index: 315569 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 3.0725. Min Range: -3.0725

Max Act: 2.0355. Min Act: -0.0000

Data Index: 355667 (C4 (Web Text))

Max Activating Token Index: 853