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

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

Neuron 2270 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: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0002

Data Index: 25997 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0955. Min Act: -0.0003

Data Index: 764416 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0912. Min Act: -0.0003

Data Index: 735335 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0896. Min Act: -0.0002

Data Index: 471685 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0881. Min Act: -0.0002

Data Index: 359259 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0854. Min Act: -0.0002

Data Index: 68014 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0836. Min Act: -0.0002

Data Index: 793 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1256009 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0843. Min Act: -0.0002

Data Index: 548773 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0834. Min Act: -0.0002

Data Index: 99825 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0829. Min Act: -0.0002

Data Index: 560357 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0815. Min Act: -0.0002

Data Index: 523831 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0800. Min Act: -0.0002

Data Index: 217602 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0800. Min Act: -0.0002

Data Index: 62015 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0812. Min Act: -0.0002

Data Index: 430621 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0812. Min Act: -0.0002

Data Index: 429435 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0827. Min Act: -0.0002

Data Index: 146336 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0830. Min Act: -0.0002

Data Index: 876178 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0821. Min Act: -0.0002

Data Index: 378993 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0798. Min Act: -0.0002

Data Index: 671420 (C4 (Web Text))

Max Activating Token Index: 605