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

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

Neuron 16 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0747. Min Range: -2.0747

Max Act: 2.0747. Min Act: -0.0000

Data Index: 1363393 (Python Code)

Max Activating Token Index: 251

Text #1

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.7789. Min Act: -0.0000

Data Index: 1392536 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1655346 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1543138 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1630629 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1462251 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1605329 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.3138. Min Act: -0.0000

Data Index: 1532547 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2838. Min Act: 0.0000

Data Index: 1543819 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1538022 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1521862 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1392776 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1559290 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1600741 (Python Code)

Max Activating Token Index: 970

Text #14

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1374476 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1507242 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1538815 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1619292 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1565664 (Python Code)

Max Activating Token Index: 458

Text #19

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1597536 (Python Code)

Max Activating Token Index: 750