Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 603 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1786. Min Act: -0.0001

Data Index: 335433 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1372. Min Act: -0.0001

Data Index: 261329 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1203932 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1048983 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1101. Min Act: -0.0001

Data Index: 594422 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1061. Min Act: -0.0001

Data Index: 540485 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0922. Min Act: -0.0001

Data Index: 977325 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0905. Min Act: -0.0001

Data Index: 48002 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0981. Min Act: -0.0001

Data Index: 853508 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0918. Min Act: -0.0001

Data Index: 262291 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1300532 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0906. Min Act: -0.0001

Data Index: 192978 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0895. Min Act: -0.0001

Data Index: 872958 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0849. Min Act: -0.0001

Data Index: 283993 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0890. Min Act: -0.0001

Data Index: 140845 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0886. Min Act: -0.0001

Data Index: 302724 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0881. Min Act: -0.0001

Data Index: 376531 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1011. Min Act: -0.0001

Data Index: 250692 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0871. Min Act: -0.0001

Data Index: 723252 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.0936. Min Act: -0.0001

Data Index: 131931 (C4 (Web Text))

Max Activating Token Index: 760