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

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

Neuron 418 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1644430 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.3435. Min Act: -0.0000

Data Index: 16027 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1390840 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1607299 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1189304 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.2118. Min Act: -0.0000

Data Index: 542489 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1362112 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1506938 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1549883 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1468174 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1569720 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1554771 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0578. Min Act: -0.0000

Data Index: 716210 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9817. Min Act: -0.0000

Data Index: 227643 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1525229 (Python Code)

Max Activating Token Index: 75

Text #15

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1585678 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1532028 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1489966 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0139. Min Act: -0.0000

Data Index: 837347 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1036649 (C4 (Web Text))

Max Activating Token Index: 221