Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1961 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1994. Min Act: -0.0002

Data Index: 389514 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1909. Min Act: -0.0002

Data Index: 739878 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1904. Min Act: -0.0002

Data Index: 261051 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1962. Min Act: -0.0002

Data Index: 624321 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1850. Min Act: -0.0001

Data Index: 398708 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1893. Min Act: -0.0001

Data Index: 389855 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1856. Min Act: -0.0002

Data Index: 727297 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1806. Min Act: -0.0002

Data Index: 13180 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1917. Min Act: -0.0002

Data Index: 228056 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1858. Min Act: -0.0002

Data Index: 694407 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1238485 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1848. Min Act: -0.0002

Data Index: 1176563 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1814. Min Act: -0.0002

Data Index: 39591 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1778. Min Act: -0.0002

Data Index: 1047237 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1814. Min Act: -0.0002

Data Index: 491016 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1823. Min Act: -0.0002

Data Index: 129871 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1841. Min Act: -0.0002

Data Index: 1112184 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1794. Min Act: -0.0002

Data Index: 696022 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1846. Min Act: -0.0001

Data Index: 554089 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.1994. Min Range: -0.1994

Max Act: 0.1790. Min Act: -0.0001

Data Index: 863740 (C4 (Web Text))

Max Activating Token Index: 284