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

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

Neuron 2139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0652. Min Range: -1.0652

Max Act: 1.0652. Min Act: -0.0000

Data Index: 174840 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.9524. Min Act: -0.0000

Data Index: 829215 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.9704. Min Act: -0.0000

Data Index: 398240 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1304072 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1290706 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1352307 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8352. Min Act: -0.0000

Data Index: 441634 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1178049 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8068. Min Act: -0.0000

Data Index: 608975 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1023185 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1242894 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7717. Min Act: -0.0000

Data Index: 285748 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7980. Min Act: -0.0000

Data Index: 167548 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8377. Min Act: -0.0000

Data Index: 325134 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8559. Min Act: -0.0000

Data Index: 207426 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1124185 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1957 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7306. Min Act: -0.0000

Data Index: 122705 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1346502 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7648. Min Act: -0.0000

Data Index: 615574 (C4 (Web Text))

Max Activating Token Index: 28