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

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

Neuron 2598 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1142102 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.4544. Min Act: -0.0000

Data Index: 903279 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2006. Min Act: -0.0000

Data Index: 538750 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2450. Min Act: -0.0000

Data Index: 798825 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2503. Min Act: -0.0000

Data Index: 870910 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1904. Min Act: -0.0000

Data Index: 787283 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1876. Min Act: -0.0000

Data Index: 673985 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1530. Min Act: -0.0000

Data Index: 555055 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1107. Min Act: -0.0000

Data Index: 395520 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1365. Min Act: -0.0000

Data Index: 126269 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.2031. Min Act: -0.0000

Data Index: 606781 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1406. Min Act: -0.0000

Data Index: 781778 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0970. Min Act: -0.0000

Data Index: 6160 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1582. Min Act: -0.0000

Data Index: 262162 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0819. Min Act: -0.0000

Data Index: 722633 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1066195 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0607. Min Act: -0.0000

Data Index: 908373 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1190514 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1055361 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.4592. Min Range: -1.4592

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1202896 (C4 (Web Text))

Max Activating Token Index: 655