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

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

Neuron 5089 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: 2.6217. Min Range: -2.6217

Max Act: 2.6217. Min Act: -0.0000

Data Index: 1596432 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.5751. Min Act: -0.0000

Data Index: 1493053 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.5277. Min Act: 0.0001

Data Index: 1439521 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.3363. Min Act: 0.0001

Data Index: 1542367 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.3531. Min Act: 0.0000

Data Index: 1367362 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.3291. Min Act: 0.0000

Data Index: 1619749 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.3185. Min Act: 0.0001

Data Index: 1504785 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.2004. Min Act: 0.0000

Data Index: 1404109 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.1694. Min Act: -0.0000

Data Index: 1418466 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.2432. Min Act: -0.0000

Data Index: 1550194 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.2523. Min Act: 0.0000

Data Index: 1458652 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.1347. Min Act: -0.0000

Data Index: 1395774 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.2174. Min Act: -0.0000

Data Index: 1647570 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.2054. Min Act: -0.0000

Data Index: 1378375 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.1615. Min Act: 0.0000

Data Index: 1600256 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1563596 (Python Code)

Max Activating Token Index: 723

Text #16

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.0727. Min Act: -0.0000

Data Index: 1555233 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 2.6217. Min Range: -2.6217

Max Act: 2.1511. Min Act: 0.0000

Data Index: 1623737 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 2.6217. Min Range: -2.6217

Max Act: 1.9770. Min Act: 0.0001

Data Index: 1362347 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 2.6217. Min Range: -2.6217

Max Act: 1.9682. Min Act: 0.0000

Data Index: 1452322 (Python Code)

Max Activating Token Index: 451