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

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

Neuron 267 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0567. Min Act: -0.0002

Data Index: 1332330 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0260. Min Act: -0.0002

Data Index: 1075733 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0279. Min Act: -0.0002

Data Index: 334209 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9928. Min Act: -0.0002

Data Index: 52600 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9862. Min Act: -0.0002

Data Index: 1224324 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9772. Min Act: -0.0002

Data Index: 1218661 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9793. Min Act: -0.0003

Data Index: 1022738 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9862. Min Act: -0.0003

Data Index: 768271 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9894. Min Act: -0.0002

Data Index: 848206 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9705. Min Act: -0.0002

Data Index: 381118 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9812. Min Act: -0.0002

Data Index: 593408 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9804. Min Act: -0.0002

Data Index: 965054 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9776. Min Act: -0.0002

Data Index: 331658 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9729. Min Act: -0.0002

Data Index: 868952 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9632. Min Act: -0.0002

Data Index: 1095486 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9770. Min Act: -0.0002

Data Index: 365871 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9694. Min Act: -0.0002

Data Index: 1217121 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9777. Min Act: -0.0002

Data Index: 827440 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9650. Min Act: -0.0002

Data Index: 1183518 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9726. Min Act: -0.0002

Data Index: 78812 (C4 (Web Text))

Max Activating Token Index: 172