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

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

Neuron 3431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1914. Min Range: -3.1914

Max Act: 3.1914. Min Act: -0.0000

Data Index: 924819 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.9115. Min Act: -0.0000

Data Index: 4878 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.8714. Min Act: -0.0000

Data Index: 1642919 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5702. Min Act: -0.0000

Data Index: 1513926 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.7861. Min Act: -0.0000

Data Index: 1597844 (Python Code)

Max Activating Token Index: 672

Text #5

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5549. Min Act: -0.0000

Data Index: 381773 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.6361. Min Act: -0.0000

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.4394. Min Act: -0.0000

Data Index: 807930 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1240972 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.3941. Min Act: -0.0000

Data Index: 101042 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.3728. Min Act: -0.0000

Data Index: 386856 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.3158. Min Act: -0.0000

Data Index: 1314599 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1518958 (Python Code)

Max Activating Token Index: 415

Text #13

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.2936. Min Act: -0.0000

Data Index: 1365196 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.2498. Min Act: -0.0000

Data Index: 594348 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.2408. Min Act: -0.0000

Data Index: 46233 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.1942. Min Act: -0.0000

Data Index: 1508618 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1612786 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.3038. Min Act: -0.0000

Data Index: 1610311 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.1801. Min Act: -0.0000

Data Index: 1017262 (C4 (Web Text))

Max Activating Token Index: 926