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

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

Neuron 2218 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: 0.5035. Min Range: -0.5035

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1380317 (Python Code)

Max Activating Token Index: 831

Text #1

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2245. Min Act: -0.0000

Data Index: 283852 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2349. Min Act: -0.0000

Data Index: 547700 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2067. Min Act: -0.0000

Data Index: 985069 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2051. Min Act: -0.0000

Data Index: 521469 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2355. Min Act: -0.0000

Data Index: 768118 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2138. Min Act: -0.0000

Data Index: 443647 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2135. Min Act: -0.0000

Data Index: 915163 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2084. Min Act: -0.0000

Data Index: 150600 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2114. Min Act: -0.0000

Data Index: 314093 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1235224 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.1885. Min Act: -0.0000

Data Index: 518201 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2085. Min Act: -0.0000

Data Index: 991941 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2137. Min Act: -0.0000

Data Index: 433475 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1591929 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1395873 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.1862. Min Act: -0.0000

Data Index: 731798 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.2003. Min Act: -0.0000

Data Index: 117132 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.1995. Min Act: -0.0000

Data Index: 576379 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.5035. Min Range: -0.5035

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1129424 (C4 (Web Text))

Max Activating Token Index: 120