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

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

Neuron 6027 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.7842. Min Act: -0.0000

Data Index: 1525345 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1480276 (Python Code)

Max Activating Token Index: 216

Text #2

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1388700 (Python Code)

Max Activating Token Index: 408

Text #3

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1527339 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1474830 (Python Code)

Max Activating Token Index: 751

Text #5

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1562954 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1620557 (Python Code)

Max Activating Token Index: 268

Text #7

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1374453 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1569495 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1503933 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1648389 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 1.7842. Min Range: -1.7842

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1561938 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1506607 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1574720 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1441614 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1656266 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1367899 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1521094 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1636483 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 1.7842. Min Range: -1.7842

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1458052 (Python Code)

Max Activating Token Index: 70