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

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

Neuron 1270 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0002

Data Index: 469819 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1220335 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0511. Min Act: -0.0002

Data Index: 842763 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1317961 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0498. Min Act: -0.0002

Data Index: 403343 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0504. Min Act: -0.0002

Data Index: 75177 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0485. Min Act: -0.0002

Data Index: 444176 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0485. Min Act: -0.0002

Data Index: 487108 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1145576 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0485. Min Act: -0.0002

Data Index: 154467 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0485. Min Act: -0.0002

Data Index: 826469 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0493. Min Act: -0.0002

Data Index: 875744 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0491. Min Act: -0.0002

Data Index: 250282 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0500. Min Act: -0.0002

Data Index: 640501 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0489. Min Act: -0.0002

Data Index: 165111 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0488. Min Act: -0.0002

Data Index: 749442 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1228941 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1030221 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1094731 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0484. Min Act: -0.0002

Data Index: 280235 (C4 (Web Text))

Max Activating Token Index: 10