Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 245 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.5250. Min Act: 0.0000

Data Index: 1583053 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.4532. Min Act: -0.0001

Data Index: 1604077 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.4355. Min Act: -0.0000

Data Index: 1414971 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.3485. Min Act: 0.0000

Data Index: 1477609 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1482671 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.3264. Min Act: -0.0000

Data Index: 1406609 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1568312 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1631753 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1643564 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2005. Min Act: 0.0000

Data Index: 1573597 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2115. Min Act: -0.0000

Data Index: 1410927 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1435560 (Python Code)

Max Activating Token Index: 99

Text #12

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.1783. Min Act: 0.0000

Data Index: 1541579 (Python Code)

Max Activating Token Index: 619

Text #13

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1387815 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1571450 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1558511 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1368716 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1564038 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1419777 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 1.5250. Min Range: -1.5250

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1492922 (Python Code)

Max Activating Token Index: 538