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

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

Neuron 5404 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: 1.3187. Min Range: -1.3187

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1405229 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 1.3187. Min Range: -1.3187

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1512470 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 1.3187. Min Range: -1.3187

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1537212 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 1.3187. Min Range: -1.3187

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1504913 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 1.3187. Min Range: -1.3187

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1494646 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 1.3187. Min Range: -1.3187

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1394379 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1455289 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1582481 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1246287 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1568109 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1465196 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1555504 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1429081 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1490300 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9500. Min Act: -0.0000

Data Index: 481023 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1612434 (Python Code)

Max Activating Token Index: 386

Text #16

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1599840 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1463872 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1435953 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 1.3187. Min Range: -1.3187

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1407253 (Python Code)

Max Activating Token Index: 178