Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 518 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0003

Data Index: 288990 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0558. Min Act: -0.0003

Data Index: 478769 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0579. Min Act: -0.0003

Data Index: 172459 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0562. Min Act: -0.0003

Data Index: 64187 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0544. Min Act: -0.0003

Data Index: 743658 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1506969 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0502. Min Act: -0.0003

Data Index: 27764 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0499. Min Act: -0.0003

Data Index: 206379 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0486. Min Act: -0.0003

Data Index: 324147 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1177663 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0478. Min Act: -0.0003

Data Index: 673511 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0483. Min Act: -0.0003

Data Index: 155630 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0483. Min Act: -0.0003

Data Index: 48749 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0451. Min Act: -0.0003

Data Index: 412814 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1011396 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1165720 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1175826 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1194452 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1330618 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0470. Min Act: -0.0003

Data Index: 255180 (C4 (Web Text))

Max Activating Token Index: 914