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

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

Neuron 190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1314. Min Act: -0.0000

Data Index: 1641008 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.4484. Min Act: -0.0000

Data Index: 1557499 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.0593. Min Act: -0.0000

Data Index: 1521505 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 3.4484. Min Range: -3.4484

Max Act: 3.1838. Min Act: -0.0000

Data Index: 1608174 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.8708. Min Act: -0.0000

Data Index: 837352 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.7311. Min Act: -0.0000

Data Index: 1600335 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.9976. Min Act: -0.0000

Data Index: 1552297 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.8253. Min Act: -0.0000

Data Index: 1566944 (Python Code)

Max Activating Token Index: 1009

Text #8

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.8255. Min Act: -0.0000

Data Index: 281442 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.6527. Min Act: -0.0000

Data Index: 1421484 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.9362. Min Act: -0.0000

Data Index: 1474698 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.7410. Min Act: -0.0000

Data Index: 1473407 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.8649. Min Act: -0.0000

Data Index: 760930 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.5548. Min Act: -0.0000

Data Index: 108662 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.6912. Min Act: -0.0000

Data Index: 893110 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.6854. Min Act: -0.0000

Data Index: 1429344 (Python Code)

Max Activating Token Index: 918

Text #16

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.6814. Min Act: -0.0000

Data Index: 650664 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.5579. Min Act: -0.0000

Data Index: 534776 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.5506. Min Act: -0.0000

Data Index: 738470 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 3.4484. Min Range: -3.4484

Max Act: 2.6556. Min Act: -0.0000

Data Index: 1005281 (C4 (Web Text))

Max Activating Token Index: 458