Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1385498 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1552699 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1438661 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 1.5004. Min Range: -1.5004

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1374202 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1386224 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1605968 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1538226 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1404060 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1487989 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1524610 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8060. Min Act: 0.0000

Data Index: 1635526 (Python Code)

Max Activating Token Index: 415

Text #11

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1510028 (Python Code)

Max Activating Token Index: 481

Text #12

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1637767 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1412702 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1619570 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1598205 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1612464 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1557672 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1617704 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 1.5004. Min Range: -1.5004

Max Act: 0.7882. Min Act: 0.0001

Data Index: 1417289 (Python Code)

Max Activating Token Index: 454