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

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

Neuron 1562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2689. Min Act: -0.0001

Data Index: 1393730 (Python Code)

Max Activating Token Index: 925

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1392044 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1461674 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2368. Min Act: -0.0000

Data Index: 408052 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1598205 (Python Code)

Max Activating Token Index: 931

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1655360 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1420090 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1367744 (Python Code)

Max Activating Token Index: 142

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1528970 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1374122 (Python Code)

Max Activating Token Index: 315

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2384. Min Act: -0.0000

Data Index: 439496 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1444525 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2196. Min Act: -0.0001

Data Index: 150976 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1347345 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1643150 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2252. Min Act: -0.0000

Data Index: 835214 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1591452 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1428019 (Python Code)

Max Activating Token Index: 579

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1423943 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1590162 (Python Code)

Max Activating Token Index: 337