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

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

Neuron 5191 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: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0002

Data Index: 941924 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0869. Min Act: -0.0002

Data Index: 38062 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1008870 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0694. Min Act: -0.0002

Data Index: 795910 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0657. Min Act: -0.0002

Data Index: 637115 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0629. Min Act: -0.0002

Data Index: 569379 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0569. Min Act: -0.0002

Data Index: 569171 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0542. Min Act: -0.0002

Data Index: 927351 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1087460 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0538. Min Act: -0.0002

Data Index: 91366 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0530. Min Act: -0.0002

Data Index: 232554 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0474. Min Act: -0.0002

Data Index: 841725 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0523. Min Act: -0.0002

Data Index: 911298 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0481. Min Act: -0.0002

Data Index: 649310 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0506. Min Act: -0.0002

Data Index: 247666 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0475. Min Act: -0.0002

Data Index: 465629 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0483. Min Act: -0.0002

Data Index: 433584 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0448. Min Act: -0.0002

Data Index: 123358 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0428. Min Act: -0.0002

Data Index: 990849 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1195516 (C4 (Web Text))

Max Activating Token Index: 618