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

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

Neuron 4720 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: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0002

Data Index: 136165 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0648. Min Act: -0.0002

Data Index: 249048 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1232705 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0577. Min Act: -0.0002

Data Index: 292464 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0574. Min Act: -0.0002

Data Index: 281857 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0526. Min Act: -0.0002

Data Index: 821352 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0545. Min Act: -0.0002

Data Index: 759837 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1133203 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0529. Min Act: -0.0002

Data Index: 670569 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0521. Min Act: -0.0002

Data Index: 723031 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1207411 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0505. Min Act: -0.0002

Data Index: 388770 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0500. Min Act: -0.0002

Data Index: 893699 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0506. Min Act: -0.0002

Data Index: 228617 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0501. Min Act: -0.0002

Data Index: 168793 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1021040 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1032008 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0515. Min Act: -0.0002

Data Index: 159181 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0505. Min Act: -0.0002

Data Index: 888218 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1010576 (C4 (Web Text))

Max Activating Token Index: 579