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

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

Neuron 4460 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0761. Min Act: -0.0003

Data Index: 974232 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0002

Data Index: 509209 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0712. Min Act: -0.0003

Data Index: 976059 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0661. Min Act: -0.0003

Data Index: 908156 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0732. Min Act: -0.0002

Data Index: 525856 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0689. Min Act: -0.0002

Data Index: 992351 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0680. Min Act: -0.0003

Data Index: 428273 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0660. Min Act: -0.0003

Data Index: 250721 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0620. Min Act: -0.0002

Data Index: 414786 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0631. Min Act: -0.0002

Data Index: 637021 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0605. Min Act: -0.0003

Data Index: 151320 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0648. Min Act: -0.0002

Data Index: 454411 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0600. Min Act: -0.0003

Data Index: 765830 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0663. Min Act: -0.0003

Data Index: 132082 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0671. Min Act: -0.0003

Data Index: 530028 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0641. Min Act: -0.0003

Data Index: 803422 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1189944 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1155682 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1330462 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0579. Min Act: -0.0003

Data Index: 697899 (C4 (Web Text))

Max Activating Token Index: 175