Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1061974 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0001

Data Index: 631577 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1115716 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1772. Min Act: -0.0001

Data Index: 236195 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1697. Min Act: -0.0001

Data Index: 237852 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1592. Min Act: -0.0001

Data Index: 33425 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1599. Min Act: -0.0001

Data Index: 198009 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1508. Min Act: -0.0001

Data Index: 425319 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1152445 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1538. Min Act: -0.0001

Data Index: 274350 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1538. Min Act: -0.0001

Data Index: 40831 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1526. Min Act: -0.0000

Data Index: 974689 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1513. Min Act: -0.0000

Data Index: 591225 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1477. Min Act: -0.0001

Data Index: 289695 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1231. Min Act: -0.0001

Data Index: 95260 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1438. Min Act: -0.0001

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1394. Min Act: -0.0001

Data Index: 848235 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1359. Min Act: -0.0001

Data Index: 608071 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1200122 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1299. Min Act: -0.0001

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 504