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

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

Neuron 3851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1600350 (Python Code)

Max Activating Token Index: 684

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1032252 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0639. Min Act: -0.0001

Data Index: 82353 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0506. Min Act: -0.0001

Data Index: 53951 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1285224 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1594895 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0538. Min Act: -0.0001

Data Index: 926556 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0517. Min Act: -0.0001

Data Index: 945378 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1090293 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0496. Min Act: -0.0001

Data Index: 57521 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0544. Min Act: -0.0001

Data Index: 525866 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0433. Min Act: -0.0001

Data Index: 784571 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0483. Min Act: -0.0001

Data Index: 344187 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0497. Min Act: -0.0001

Data Index: 720858 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1275098 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0505. Min Act: -0.0001

Data Index: 274002 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1533978 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0478. Min Act: -0.0001

Data Index: 964979 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0452. Min Act: -0.0001

Data Index: 678618 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1271965 (C4 (Web Text))

Max Activating Token Index: 589