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

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

Neuron 2240 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.9142. Min Act: -0.0000

Data Index: 447315 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 3.2496. Min Range: -3.2496

Max Act: 3.2496. Min Act: -0.0000

Data Index: 587254 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.8466. Min Act: -0.0000

Data Index: 590819 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.8000. Min Act: -0.0000

Data Index: 876971 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.8430. Min Act: -0.0000

Data Index: 214975 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.6816. Min Act: -0.0000

Data Index: 869397 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.4832. Min Act: -0.0000

Data Index: 566396 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.5265. Min Act: -0.0000

Data Index: 244693 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1004788 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.4733. Min Act: -0.0000

Data Index: 909572 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.3328. Min Act: -0.0000

Data Index: 873750 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.7265. Min Act: -0.0000

Data Index: 691175 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.4645. Min Act: -0.0000

Data Index: 1152786 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.7231. Min Act: -0.0000

Data Index: 440244 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.5247. Min Act: -0.0000

Data Index: 52666 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.5409. Min Act: -0.0000

Data Index: 191512 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.5468. Min Act: -0.0000

Data Index: 423330 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.5265. Min Act: -0.0000

Data Index: 281204 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1224303 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 3.2496. Min Range: -3.2496

Max Act: 2.3736. Min Act: -0.0000

Data Index: 297496 (C4 (Web Text))

Max Activating Token Index: 146