Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 36 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0003

Data Index: 360905 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1024542 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0397. Min Act: -0.0003

Data Index: 879893 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1537128 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1397716 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0335. Min Act: -0.0003

Data Index: 825383 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1630600 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1530451 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1209601 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0315. Min Act: -0.0003

Data Index: 590706 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1390129 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1654770 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1410576 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1585360 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0345. Min Act: -0.0003

Data Index: 232884 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1550911 (Python Code)

Max Activating Token Index: 620

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1610214 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0309. Min Act: -0.0003

Data Index: 155740 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1525709 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1032272 (C4 (Web Text))

Max Activating Token Index: 202