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

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

Neuron 1845 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: 1.3541. Min Range: -1.3541

Max Act: 1.3541. Min Act: -0.0000

Data Index: 219376 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1824. Min Act: -0.0000

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.2192. Min Act: -0.0000

Data Index: 520810 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1256608 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1525. Min Act: -0.0000

Data Index: 258607 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1769. Min Act: -0.0000

Data Index: 754856 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0740. Min Act: -0.0000

Data Index: 1180869 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0330. Min Act: -0.0000

Data Index: 324501 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0581. Min Act: -0.0000

Data Index: 925400 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.3541. Min Range: -1.3541

Max Act: 0.9365. Min Act: -0.0000

Data Index: 906863 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1325157 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1039757 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0272. Min Act: -0.0000

Data Index: 137891 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1122808 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.3541. Min Range: -1.3541

Max Act: 0.9550. Min Act: -0.0000

Data Index: 756162 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.3541. Min Range: -1.3541

Max Act: 1.0406. Min Act: -0.0000

Data Index: 576936 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.3541. Min Range: -1.3541

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1094978 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.3541. Min Range: -1.3541

Max Act: 0.9966. Min Act: -0.0000

Data Index: 559812 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 1.3541. Min Range: -1.3541

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1333254 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.3541. Min Range: -1.3541

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1303602 (C4 (Web Text))

Max Activating Token Index: 272