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

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

Neuron 167 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: 0.0861. Min Range: -0.0861

Max Act: 0.0737. Min Act: -0.0000

Data Index: 195946 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 259838 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0812. Min Act: -0.0000

Data Index: 853402 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0688. Min Act: -0.0000

Data Index: 767334 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1309217 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1358553 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0637. Min Act: -0.0000

Data Index: 100283 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0601. Min Act: -0.0000

Data Index: 873669 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0588. Min Act: -0.0000

Data Index: 352630 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0610. Min Act: -0.0000

Data Index: 14744 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0578. Min Act: -0.0000

Data Index: 794186 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0598. Min Act: -0.0000

Data Index: 431450 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0567. Min Act: -0.0000

Data Index: 738032 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0588. Min Act: -0.0000

Data Index: 115572 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0562. Min Act: -0.0000

Data Index: 64628 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1232459 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0547. Min Act: -0.0000

Data Index: 861505 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1160772 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0559. Min Act: -0.0000

Data Index: 295399 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0530. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 394