Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2841 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0531. Min Act: -0.0001

Data Index: 666517 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0481. Min Act: -0.0001

Data Index: 220597 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0468. Min Act: -0.0001

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1114466 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0448. Min Act: -0.0001

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1242242 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1386011 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1525165 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0441. Min Act: -0.0001

Data Index: 223305 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1585726 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1396258 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1439865 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0368. Min Act: -0.0001

Data Index: 815011 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1490502 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1625417 (Python Code)

Max Activating Token Index: 839

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1617539 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1418728 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1639161 (Python Code)

Max Activating Token Index: 259