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

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

Neuron 2681 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: 0.0540. Min Range: -0.0540

Max Act: 0.0534. Min Act: -0.0003

Data Index: 596466 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0003

Data Index: 619255 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0505. Min Act: -0.0003

Data Index: 623978 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0512. Min Act: -0.0003

Data Index: 287194 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0495. Min Act: -0.0003

Data Index: 285383 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1344691 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0489. Min Act: -0.0003

Data Index: 563599 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1280152 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1006902 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1340631 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0486. Min Act: -0.0003

Data Index: 536827 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0465. Min Act: -0.0003

Data Index: 398285 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0449. Min Act: -0.0003

Data Index: 835484 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0446. Min Act: -0.0003

Data Index: 789638 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0439. Min Act: -0.0003

Data Index: 309154 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0453. Min Act: -0.0003

Data Index: 343197 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0433. Min Act: -0.0003

Data Index: 788109 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0428. Min Act: -0.0003

Data Index: 324577 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0419. Min Act: -0.0003

Data Index: 9537 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0431. Min Act: -0.0003

Data Index: 929133 (C4 (Web Text))

Max Activating Token Index: 204