Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3583 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0539. Min Act: -0.0002

Data Index: 143304 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0487. Min Act: -0.0002

Data Index: 138751 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0513. Min Act: -0.0002

Data Index: 275448 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0497. Min Act: -0.0002

Data Index: 188609 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1214691 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0441. Min Act: -0.0002

Data Index: 29805 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0458. Min Act: -0.0002

Data Index: 10387 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1272159 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0452. Min Act: -0.0002

Data Index: 256713 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0442. Min Act: -0.0002

Data Index: 928693 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0450. Min Act: -0.0002

Data Index: 780243 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1255072 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0448. Min Act: -0.0002

Data Index: 106865 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1101257 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0441. Min Act: -0.0002

Data Index: 692241 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0442. Min Act: -0.0002

Data Index: 311633 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0438. Min Act: -0.0002

Data Index: 345339 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1300702 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0455. Min Act: -0.0002

Data Index: 992410 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0438. Min Act: -0.0002

Data Index: 658397 (C4 (Web Text))

Max Activating Token Index: 949