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

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

Neuron 5036 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: 0.9248. Min Range: -0.9248

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1448537 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6706. Min Act: -0.0000

Data Index: 334328 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1508974 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1476224 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1451489 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1580873 (Python Code)

Max Activating Token Index: 836

Text #6

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1645285 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1519527 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1646460 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1618527 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1521221 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1581768 (Python Code)

Max Activating Token Index: 651

Text #12

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1552572 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1597740 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1412142 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1643618 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1463054 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1457366 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1397276 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1511339 (Python Code)

Max Activating Token Index: 95