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

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

Neuron 1043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1604935 (Python Code)

Max Activating Token Index: 291

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1745. Min Act: -0.0000

Data Index: 984937 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1591. Min Act: -0.0001

Data Index: 5082 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1553574 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1683. Min Act: -0.0001

Data Index: 897466 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1607. Min Act: -0.0001

Data Index: 346877 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1602. Min Act: -0.0001

Data Index: 190315 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1543. Min Act: -0.0001

Data Index: 674876 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1143396 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1481. Min Act: -0.0001

Data Index: 505652 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1049989 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1425. Min Act: -0.0000

Data Index: 848675 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1467. Min Act: -0.0000

Data Index: 43630 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1458. Min Act: -0.0000

Data Index: 726886 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1512. Min Act: -0.0000

Data Index: 813087 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1626360 (Python Code)

Max Activating Token Index: 417

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1440. Min Act: -0.0000

Data Index: 297103 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1426. Min Act: -0.0000

Data Index: 437840 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1142227 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1392. Min Act: -0.0000

Data Index: 609346 (C4 (Web Text))

Max Activating Token Index: 247