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

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

Neuron 2408 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0001

Data Index: 444177 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0666. Min Act: -0.0001

Data Index: 247930 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0608. Min Act: -0.0001

Data Index: 568682 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1124611 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0612. Min Act: -0.0001

Data Index: 480905 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0584. Min Act: -0.0001

Data Index: 137280 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0597. Min Act: -0.0001

Data Index: 624827 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0547. Min Act: -0.0001

Data Index: 841180 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1005347 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0562. Min Act: -0.0001

Data Index: 282033 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1019097 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0567. Min Act: -0.0001

Data Index: 126237 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0570. Min Act: -0.0001

Data Index: 328090 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0549. Min Act: -0.0001

Data Index: 935344 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0564. Min Act: -0.0001

Data Index: 420212 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0535. Min Act: -0.0001

Data Index: 839806 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0545. Min Act: -0.0001

Data Index: 820368 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1100094 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1179193 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0519. Min Act: -0.0001

Data Index: 818403 (C4 (Web Text))

Max Activating Token Index: 462