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

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

Neuron 4243 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1948. Min Act: -0.0001

Data Index: 52238 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1919. Min Act: -0.0001

Data Index: 635169 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1947. Min Act: -0.0001

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1863. Min Act: -0.0001

Data Index: 326918 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1773. Min Act: -0.0001

Data Index: 497149 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1725. Min Act: -0.0001

Data Index: 96091 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1146255 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1487. Min Act: -0.0001

Data Index: 531178 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1545. Min Act: -0.0001

Data Index: 582572 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1640. Min Act: -0.0001

Data Index: 298508 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1231858 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1445. Min Act: -0.0001

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1459. Min Act: -0.0001

Data Index: 660496 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1608. Min Act: -0.0001

Data Index: 141051 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1320181 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1353. Min Act: -0.0001

Data Index: 465547 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1574. Min Act: -0.0001

Data Index: 452025 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1383. Min Act: -0.0001

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.1948. Min Range: -0.1948

Max Act: 0.1533. Min Act: -0.0001

Data Index: 917463 (C4 (Web Text))

Max Activating Token Index: 700