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

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

Neuron 2852 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: 0.8054. Min Range: -0.8054

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1164481 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7748. Min Act: -0.0000

Data Index: 646731 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7938. Min Act: -0.0000

Data Index: 636333 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1105529 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7494. Min Act: -0.0000

Data Index: 452291 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7038. Min Act: -0.0000

Data Index: 412864 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7012. Min Act: -0.0000

Data Index: 43771 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6880. Min Act: -0.0000

Data Index: 915576 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6895. Min Act: -0.0000

Data Index: 432695 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1045852 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7023. Min Act: -0.0000

Data Index: 820433 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6636. Min Act: -0.0000

Data Index: 187698 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6568. Min Act: -0.0000

Data Index: 938142 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6314. Min Act: -0.0000

Data Index: 124123 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6391. Min Act: -0.0000

Data Index: 584621 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6356. Min Act: -0.0000

Data Index: 676423 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1042402 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6093. Min Act: -0.0000

Data Index: 872102 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5982. Min Act: -0.0000

Data Index: 469216 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6207. Min Act: -0.0000

Data Index: 125875 (C4 (Web Text))

Max Activating Token Index: 412