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

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

Neuron 824 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0001

Data Index: 418932 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5340. Min Act: -0.0001

Data Index: 698619 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1012817 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4904. Min Act: -0.0001

Data Index: 879252 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4224. Min Act: -0.0001

Data Index: 738743 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1134254 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4669. Min Act: -0.0001

Data Index: 780419 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1096670 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4035. Min Act: -0.0001

Data Index: 381911 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4284. Min Act: -0.0001

Data Index: 1243754 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3854. Min Act: -0.0001

Data Index: 510206 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4036. Min Act: -0.0001

Data Index: 903783 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4079. Min Act: -0.0001

Data Index: 216835 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3574. Min Act: -0.0001

Data Index: 375331 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1134133 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3638. Min Act: -0.0001

Data Index: 662762 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3751. Min Act: -0.0001

Data Index: 984567 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3647. Min Act: -0.0001

Data Index: 1212304 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3664. Min Act: -0.0001

Data Index: 292329 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.3839. Min Act: -0.0001

Data Index: 20798 (C4 (Web Text))

Max Activating Token Index: 209