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

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

Neuron 5035 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0000

Data Index: 40836 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0686. Min Act: -0.0000

Data Index: 557962 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1286825 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0615. Min Act: -0.0000

Data Index: 156651 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0673. Min Act: -0.0000

Data Index: 977513 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0602. Min Act: -0.0000

Data Index: 168295 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1128594 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0552. Min Act: -0.0000

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0524. Min Act: -0.0000

Data Index: 74451 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0558. Min Act: -0.0000

Data Index: 668277 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1522075 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0551. Min Act: -0.0000

Data Index: 417535 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0507. Min Act: -0.0000

Data Index: 543646 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0502. Min Act: -0.0000

Data Index: 548193 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0529. Min Act: -0.0000

Data Index: 338215 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0478. Min Act: -0.0000

Data Index: 305646 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0496. Min Act: -0.0000

Data Index: 480550 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1086274 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0498. Min Act: -0.0000

Data Index: 220116 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0468. Min Act: -0.0000

Data Index: 645301 (C4 (Web Text))

Max Activating Token Index: 22