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

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

Neuron 1266 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: 2.4470. Min Range: -2.4470

Max Act: 2.4470. Min Act: -0.0000

Data Index: 656403 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.4335. Min Act: -0.0000

Data Index: 514613 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1977. Min Act: -0.0000

Data Index: 770843 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2376. Min Act: -0.0000

Data Index: 645704 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2113. Min Act: -0.0000

Data Index: 524683 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1864. Min Act: -0.0000

Data Index: 464378 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.0847. Min Act: -0.0000

Data Index: 29799 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1723. Min Act: -0.0000

Data Index: 1282684 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1397. Min Act: -0.0000

Data Index: 69016 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.0950. Min Act: -0.0000

Data Index: 584767 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.0829. Min Act: -0.0000

Data Index: 986967 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.0884. Min Act: -0.0000

Data Index: 906418 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1948. Min Act: -0.0000

Data Index: 973030 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1700. Min Act: -0.0000

Data Index: 801460 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1301. Min Act: -0.0000

Data Index: 1110540 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 2.4470. Min Range: -2.4470

Max Act: 1.9605. Min Act: -0.0000

Data Index: 1027005 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 2.4470. Min Range: -2.4470

Max Act: 1.9624. Min Act: -0.0000

Data Index: 304225 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 2.4470. Min Range: -2.4470

Max Act: 1.9369. Min Act: -0.0000

Data Index: 970063 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 2.4470. Min Range: -2.4470

Max Act: 1.9120. Min Act: -0.0000

Data Index: 509269 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 2.4470. Min Range: -2.4470

Max Act: 1.9040. Min Act: -0.0000

Data Index: 111829 (C4 (Web Text))

Max Activating Token Index: 613