Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2158 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2114. Min Act: -0.0000

Data Index: 596280 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1748. Min Act: -0.0001

Data Index: 671674 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1307763 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1646. Min Act: -0.0000

Data Index: 417163 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1441. Min Act: -0.0000

Data Index: 223411 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1545. Min Act: -0.0000

Data Index: 990665 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1542. Min Act: -0.0000

Data Index: 160951 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1546. Min Act: -0.0001

Data Index: 513845 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1221286 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1481. Min Act: -0.0001

Data Index: 295115 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1469. Min Act: -0.0000

Data Index: 999857 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1315. Min Act: -0.0000

Data Index: 258700 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1353. Min Act: -0.0000

Data Index: 276231 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1040408 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1284. Min Act: -0.0000

Data Index: 714528 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1362. Min Act: -0.0000

Data Index: 750220 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1213818 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1414. Min Act: -0.0001

Data Index: 552015 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1462. Min Act: -0.0000

Data Index: 260138 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1412. Min Act: -0.0001

Data Index: 278869 (C4 (Web Text))

Max Activating Token Index: 338