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

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

Neuron 2186 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1040479 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6392. Min Act: -0.0000

Data Index: 172248 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6072. Min Act: -0.0000

Data Index: 978222 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1287155 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5918. Min Act: -0.0000

Data Index: 225827 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5294. Min Act: -0.0000

Data Index: 823207 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1144979 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5351. Min Act: -0.0000

Data Index: 679423 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5681. Min Act: -0.0000

Data Index: 120012 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5293. Min Act: -0.0000

Data Index: 290945 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5636. Min Act: -0.0000

Data Index: 576667 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5392. Min Act: -0.0000

Data Index: 145792 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5080. Min Act: -0.0000

Data Index: 257359 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1084541 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.5109. Min Act: -0.0000

Data Index: 942033 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.4925. Min Act: -0.0000

Data Index: 883276 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1258452 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.4248. Min Act: -0.0000

Data Index: 50768 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.4990. Min Act: -0.0000

Data Index: 895288 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.9491. Min Range: -0.9491

Max Act: 0.4788. Min Act: -0.0000

Data Index: 251203 (C4 (Web Text))

Max Activating Token Index: 764