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

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

Neuron 2435 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: 1.4225. Min Range: -1.4225

Max Act: 1.4225. Min Act: -0.0000

Data Index: 1451589 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1485568 (Python Code)

Max Activating Token Index: 749

Text #2

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1497984 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1526537 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.2084. Min Act: -0.0000

Data Index: 1421443 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1475930 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3341. Min Act: -0.0000

Data Index: 1498874 (Python Code)

Max Activating Token Index: 865

Text #7

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1656634 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1526200 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1618416 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1463605 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1544901 (Python Code)

Max Activating Token Index: 360

Text #12

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1483338 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1590335 (Python Code)

Max Activating Token Index: 480

Text #14

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1606479 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1437600 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 1.4225. Min Range: -1.4225

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1402244 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 1.4225. Min Range: -1.4225

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1579990 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 1.4225. Min Range: -1.4225

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1362957 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 1.4225. Min Range: -1.4225

Max Act: 0.9129. Min Act: -0.0000

Data Index: 612866 (C4 (Web Text))

Max Activating Token Index: 886