Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0408. Min Range: -2.0408

Max Act: 2.0252. Min Act: -0.0000

Data Index: 960536 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 2.0408. Min Range: -2.0408

Max Act: 2.0408. Min Act: -0.0000

Data Index: 907902 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.7115. Min Act: -0.0000

Data Index: 633483 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.7350. Min Act: -0.0000

Data Index: 390213 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.7218. Min Act: -0.0000

Data Index: 797909 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5513. Min Act: -0.0000

Data Index: 24460 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.8095. Min Act: -0.0000

Data Index: 443803 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5780. Min Act: -0.0000

Data Index: 345491 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1045966 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5774. Min Act: -0.0000

Data Index: 1004125 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1137735 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1001218 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5683. Min Act: -0.0000

Data Index: 685523 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1303232 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.3850. Min Act: -0.0000

Data Index: 299117 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1155328 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.5333. Min Act: -0.0000

Data Index: 15267 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.4043. Min Act: -0.0000

Data Index: 639074 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.3622. Min Act: -0.0000

Data Index: 546833 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 2.0408. Min Range: -2.0408

Max Act: 1.4061. Min Act: -0.0000

Data Index: 478073 (C4 (Web Text))

Max Activating Token Index: 335