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

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

Neuron 2712 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1674. Min Act: -0.0001

Data Index: 871033 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1323103 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1730. Min Act: -0.0001

Data Index: 144161 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1638. Min Act: -0.0001

Data Index: 390356 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1448. Min Act: -0.0001

Data Index: 328062 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1636. Min Act: -0.0001

Data Index: 544020 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1356574 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1549. Min Act: -0.0001

Data Index: 50114 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1124028 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1595. Min Act: -0.0001

Data Index: 746652 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1518. Min Act: -0.0001

Data Index: 689796 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1569. Min Act: -0.0001

Data Index: 324122 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1173576 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1552. Min Act: -0.0001

Data Index: 687807 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1536. Min Act: -0.0001

Data Index: 648339 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1393. Min Act: -0.0001

Data Index: 139154 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1283387 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1482. Min Act: -0.0001

Data Index: 562344 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1409. Min Act: -0.0001

Data Index: 109385 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1205967 (C4 (Web Text))

Max Activating Token Index: 1017