Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1063102 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0454. Min Act: -0.0002

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1317858 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1639655 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1028080 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1631355 (Python Code)

Max Activating Token Index: 105

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0526. Min Act: -0.0001

Data Index: 149429 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0517. Min Act: -0.0002

Data Index: 436763 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0485. Min Act: -0.0001

Data Index: 917211 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1636931 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1417222 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0449. Min Act: -0.0001

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1366204 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0493. Min Act: -0.0001

Data Index: 1655618 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0506. Min Act: -0.0001

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1417131 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0472. Min Act: -0.0001

Data Index: 344882 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0440. Min Act: -0.0002

Data Index: 643858 (C4 (Web Text))

Max Activating Token Index: 131