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

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

Neuron 2667 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.2826. Min Act: -0.0000

Data Index: 787578 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.0528. Min Act: -0.0000

Data Index: 827633 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9904. Min Act: -0.0000

Data Index: 654969 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1200706 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9317. Min Act: -0.0000

Data Index: 724069 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9093. Min Act: -0.0000

Data Index: 395064 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1134919 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9214. Min Act: -0.0000

Data Index: 538848 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8605. Min Act: -0.0000

Data Index: 339165 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8551. Min Act: -0.0000

Data Index: 184673 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8842. Min Act: -0.0000

Data Index: 441167 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1095246 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.7795. Min Act: -0.0000

Data Index: 932398 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8760. Min Act: -0.0000

Data Index: 20994 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8308. Min Act: -0.0000

Data Index: 117047 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8498. Min Act: -0.0000

Data Index: 626787 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1152370 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8230. Min Act: -0.0000

Data Index: 540043 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1111862 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.7860. Min Act: -0.0000

Data Index: 409799 (C4 (Web Text))

Max Activating Token Index: 734