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

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

Neuron 546 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2495. Min Range: -4.2495

Max Act: 4.2495. Min Act: -0.0000

Data Index: 502516 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.2800. Min Act: -0.0000

Data Index: 882847 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.1917. Min Act: -0.0000

Data Index: 204984 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.1616. Min Act: -0.0000

Data Index: 1460582 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.2079. Min Act: -0.0000

Data Index: 795327 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.1595. Min Act: -0.0000

Data Index: 147262 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.1417. Min Act: -0.0000

Data Index: 1142371 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.9516. Min Act: -0.0000

Data Index: 1357021 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.8094. Min Act: -0.0000

Data Index: 56371 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 4.2495. Min Range: -4.2495

Max Act: 3.0886. Min Act: -0.0000

Data Index: 87841 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.8896. Min Act: -0.0000

Data Index: 1613251 (Python Code)

Max Activating Token Index: 518

Text #11

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.7967. Min Act: -0.0000

Data Index: 211920 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1164124 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.7735. Min Act: -0.0000

Data Index: 658187 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.7122. Min Act: -0.0000

Data Index: 1503278 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.5607. Min Act: -0.0000

Data Index: 518762 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.6687. Min Act: -0.0000

Data Index: 538996 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.6198. Min Act: -0.0000

Data Index: 1551165 (Python Code)

Max Activating Token Index: 523

Text #18

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.6194. Min Act: -0.0000

Data Index: 941252 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 4.2495. Min Range: -4.2495

Max Act: 2.7477. Min Act: -0.0000

Data Index: 848984 (C4 (Web Text))

Max Activating Token Index: 28