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

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

Neuron 3656 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: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0002

Data Index: 289331 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0724. Min Act: -0.0002

Data Index: 753863 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0709. Min Act: -0.0002

Data Index: 914047 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0709. Min Act: -0.0002

Data Index: 536969 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0672. Min Act: -0.0002

Data Index: 62164 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0621. Min Act: -0.0002

Data Index: 275472 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0604. Min Act: -0.0002

Data Index: 565411 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0627. Min Act: -0.0002

Data Index: 114109 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0585. Min Act: -0.0002

Data Index: 568928 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1173877 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0575. Min Act: -0.0002

Data Index: 201149 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0565. Min Act: -0.0002

Data Index: 368956 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0567. Min Act: -0.0002

Data Index: 634399 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0560. Min Act: -0.0002

Data Index: 803790 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0537. Min Act: -0.0002

Data Index: 70474 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0575. Min Act: -0.0002

Data Index: 978901 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0558. Min Act: -0.0002

Data Index: 945054 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0552. Min Act: -0.0002

Data Index: 396449 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1003604 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0553. Min Act: -0.0002

Data Index: 232013 (C4 (Web Text))

Max Activating Token Index: 157