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

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

Neuron 2989 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9380. Min Act: -0.0001

Data Index: 200401 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9602. Min Act: -0.0001

Data Index: 1267558 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8037. Min Act: -0.0001

Data Index: 359487 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7947. Min Act: -0.0001

Data Index: 195596 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8211. Min Act: -0.0001

Data Index: 811308 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7829. Min Act: -0.0001

Data Index: 284852 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7887. Min Act: -0.0001

Data Index: 483276 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1048584 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7526. Min Act: -0.0001

Data Index: 888705 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7470. Min Act: -0.0001

Data Index: 616998 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7118. Min Act: -0.0001

Data Index: 662855 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7748. Min Act: -0.0001

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7048. Min Act: -0.0001

Data Index: 276877 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7063. Min Act: -0.0001

Data Index: 4908 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.6749. Min Act: -0.0001

Data Index: 267363 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.6918. Min Act: -0.0001

Data Index: 107691 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1259164 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7486. Min Act: -0.0001

Data Index: 1346002 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.6788. Min Act: -0.0001

Data Index: 1100030 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1209658 (C4 (Web Text))

Max Activating Token Index: 535