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

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

Neuron 860 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2849. Min Act: -0.0000

Data Index: 987617 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2674. Min Act: -0.0000

Data Index: 560134 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1517609 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1623483 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1600192 (Python Code)

Max Activating Token Index: 196

Text #5

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2339. Min Act: -0.0000

Data Index: 106010 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2271. Min Act: -0.0000

Data Index: 802716 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1415873 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1353493 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1376071 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.2001. Min Act: -0.0000

Data Index: 745952 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1606441 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1999. Min Act: -0.0000

Data Index: 650215 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1917. Min Act: -0.0000

Data Index: 561569 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1914. Min Act: -0.0000

Data Index: 70245 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1957. Min Act: -0.0000

Data Index: 51548 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1445672 (Python Code)

Max Activating Token Index: 745

Text #17

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1925. Min Act: -0.0000

Data Index: 209885 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1921. Min Act: -0.0000

Data Index: 312739 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.2849. Min Range: -0.2849

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1397790 (Python Code)

Max Activating Token Index: 819