Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5389 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1302267 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0708. Min Act: -0.0002

Data Index: 347592 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0706. Min Act: -0.0002

Data Index: 719132 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1055875 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0697. Min Act: -0.0002

Data Index: 914316 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0661. Min Act: -0.0002

Data Index: 896295 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0651. Min Act: -0.0002

Data Index: 41281 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0668. Min Act: -0.0002

Data Index: 58329 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0613. Min Act: -0.0002

Data Index: 702514 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0586. Min Act: -0.0002

Data Index: 681559 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0606. Min Act: -0.0002

Data Index: 69408 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0607. Min Act: -0.0002

Data Index: 304216 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0599. Min Act: -0.0002

Data Index: 263493 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1052224 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0593. Min Act: -0.0002

Data Index: 729944 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0586. Min Act: -0.0002

Data Index: 876621 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0589. Min Act: -0.0002

Data Index: 200359 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0565. Min Act: -0.0002

Data Index: 850737 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1101569 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0583. Min Act: -0.0002

Data Index: 371777 (C4 (Web Text))

Max Activating Token Index: 562