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

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

Neuron 3561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2655. Min Range: -2.2655

Max Act: 2.2655. Min Act: -0.0000

Data Index: 1237645 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 2.2655. Min Range: -2.2655

Max Act: 2.0725. Min Act: -0.0000

Data Index: 660575 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.7091. Min Act: -0.0000

Data Index: 77539 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1315515 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.6449. Min Act: -0.0000

Data Index: 276449 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.7323. Min Act: -0.0000

Data Index: 624825 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.5171. Min Act: -0.0000

Data Index: 175485 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.5943. Min Act: -0.0000

Data Index: 607351 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.6364. Min Act: -0.0000

Data Index: 962175 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.5846. Min Act: -0.0000

Data Index: 222153 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.6106. Min Act: -0.0000

Data Index: 903287 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.5684. Min Act: -0.0000

Data Index: 49787 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.4894. Min Act: -0.0000

Data Index: 930577 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.3998. Min Act: -0.0000

Data Index: 1132019 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.2757. Min Act: -0.0000

Data Index: 17432 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1094959 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.3810. Min Act: -0.0000

Data Index: 212858 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.2970. Min Act: -0.0000

Data Index: 420180 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.3032. Min Act: -0.0000

Data Index: 343144 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 2.2655. Min Range: -2.2655

Max Act: 1.2914. Min Act: -0.0000

Data Index: 610790 (C4 (Web Text))

Max Activating Token Index: 37