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

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

Neuron 4869 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1224825 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0780. Min Act: -0.0002

Data Index: 642002 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0733. Min Act: -0.0002

Data Index: 462600 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0635. Min Act: -0.0002

Data Index: 479578 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0643. Min Act: -0.0002

Data Index: 956752 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0707. Min Act: -0.0002

Data Index: 855429 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0760. Min Act: -0.0002

Data Index: 577148 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1166699 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0657. Min Act: -0.0002

Data Index: 529262 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1297493 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0660. Min Act: -0.0002

Data Index: 840170 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0644. Min Act: -0.0002

Data Index: 468844 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1291191 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0697. Min Act: -0.0002

Data Index: 723271 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0645. Min Act: -0.0002

Data Index: 438190 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0668. Min Act: -0.0002

Data Index: 937786 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0628. Min Act: -0.0002

Data Index: 586072 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0631. Min Act: -0.0002

Data Index: 719717 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1280427 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0670. Min Act: -0.0002

Data Index: 235379 (C4 (Web Text))

Max Activating Token Index: 923