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

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

Neuron 4558 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1498. Min Range: -5.1498

Max Act: 5.1498. Min Act: -0.0000

Data Index: 587781 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.8414. Min Act: -0.0000

Data Index: 762258 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.5953. Min Act: -0.0000

Data Index: 202210 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.6173. Min Act: -0.0000

Data Index: 1184069 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.3673. Min Act: -0.0000

Data Index: 495456 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.4422. Min Act: -0.0000

Data Index: 630229 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.2091. Min Act: -0.0000

Data Index: 863775 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.3853. Min Act: -0.0000

Data Index: 207915 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 5.1498. Min Range: -5.1498

Max Act: 3.9452. Min Act: -0.0000

Data Index: 933035 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.1289. Min Act: -0.0000

Data Index: 437684 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.2543. Min Act: -0.0000

Data Index: 684539 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.0262. Min Act: -0.0000

Data Index: 36399 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.3358. Min Act: -0.0000

Data Index: 405283 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.1424. Min Act: -0.0000

Data Index: 1330044 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 5.1498. Min Range: -5.1498

Max Act: 3.9704. Min Act: -0.0000

Data Index: 533820 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 5.1498. Min Range: -5.1498

Max Act: 3.8793. Min Act: -0.0000

Data Index: 547126 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 5.1498. Min Range: -5.1498

Max Act: 3.8497. Min Act: -0.0000

Data Index: 969610 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 5.1498. Min Range: -5.1498

Max Act: 4.1708. Min Act: -0.0000

Data Index: 1107673 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 5.1498. Min Range: -5.1498

Max Act: 3.9712. Min Act: -0.0000

Data Index: 1032329 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 5.1498. Min Range: -5.1498

Max Act: 3.7614. Min Act: -0.0000

Data Index: 787346 (C4 (Web Text))

Max Activating Token Index: 598