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

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

Neuron 3529 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: 1.1011. Min Range: -1.1011

Max Act: 1.1011. Min Act: -0.0000

Data Index: 509858 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9031. Min Act: -0.0000

Data Index: 638582 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8249. Min Act: -0.0000

Data Index: 704798 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1312240 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1016993 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8402. Min Act: -0.0000

Data Index: 270430 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8716. Min Act: -0.0000

Data Index: 279267 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8372. Min Act: -0.0000

Data Index: 288997 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8132. Min Act: -0.0000

Data Index: 566881 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8890. Min Act: -0.0000

Data Index: 729143 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1169913 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8352. Min Act: -0.0000

Data Index: 128394 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.7999. Min Act: -0.0000

Data Index: 929651 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1149133 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.7321. Min Act: -0.0000

Data Index: 467062 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.7683. Min Act: -0.0000

Data Index: 796591 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.7801. Min Act: -0.0000

Data Index: 325530 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1288715 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8015. Min Act: -0.0000

Data Index: 464519 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.1011. Min Range: -1.1011

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1022427 (C4 (Web Text))

Max Activating Token Index: 934