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

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

Neuron 406 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1471837 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1405825 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1653492 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1376385 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1573900 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1546872 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1605469 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1520732 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1592000 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1444650 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1390672 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1605570 (Python Code)

Max Activating Token Index: 736

Text #12

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1500273 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1631926 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1514844 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1515433 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1397205 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1476040 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1607367 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1466513 (Python Code)

Max Activating Token Index: 334