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

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

Neuron 1444 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.9669. Min Act: -0.0000

Data Index: 218073 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8319. Min Act: -0.0000

Data Index: 606059 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1183789 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6766. Min Act: -0.0000

Data Index: 693593 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6969. Min Act: -0.0000

Data Index: 763987 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6840. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1284513 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1245706 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6652. Min Act: -0.0000

Data Index: 333612 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1003740 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6374. Min Act: -0.0000

Data Index: 687741 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1331424 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1010763 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.5831. Min Act: -0.0000

Data Index: 904548 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6196. Min Act: -0.0000

Data Index: 79251 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.5981. Min Act: -0.0000

Data Index: 334416 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6141. Min Act: -0.0000

Data Index: 149473 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.5907. Min Act: -0.0000

Data Index: 584413 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6015. Min Act: -0.0000

Data Index: 827881 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6005. Min Act: -0.0000

Data Index: 126866 (C4 (Web Text))

Max Activating Token Index: 891