Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1938 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5806. Min Act: -0.0003

Data Index: 871294 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5653. Min Act: -0.0003

Data Index: 341593 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.6072. Min Act: -0.0003

Data Index: 462711 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5981. Min Act: -0.0003

Data Index: 106710 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5653. Min Act: -0.0003

Data Index: 1290746 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5589. Min Act: -0.0003

Data Index: 972975 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5065. Min Act: -0.0003

Data Index: 1099657 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5083. Min Act: -0.0003

Data Index: 786570 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5200. Min Act: -0.0003

Data Index: 1245679 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4642. Min Act: -0.0003

Data Index: 746770 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4886. Min Act: -0.0003

Data Index: 888935 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4391. Min Act: -0.0003

Data Index: 297113 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4577. Min Act: -0.0003

Data Index: 687506 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4583. Min Act: -0.0003

Data Index: 479529 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4864. Min Act: -0.0003

Data Index: 156422 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4795. Min Act: -0.0003

Data Index: 329352 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4479. Min Act: -0.0003

Data Index: 1106256 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4323. Min Act: -0.0003

Data Index: 713348 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4614. Min Act: -0.0003

Data Index: 571491 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4589. Min Act: -0.0003

Data Index: 497042 (C4 (Web Text))

Max Activating Token Index: 236