Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3348 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3284. Min Act: -0.0001

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.3156. Min Act: -0.0000

Data Index: 840246 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2494. Min Act: -0.0001

Data Index: 12609 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2517. Min Act: -0.0001

Data Index: 362036 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2191. Min Act: -0.0001

Data Index: 510971 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1034932 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1267831 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.2074. Min Act: -0.0001

Data Index: 220038 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1298394 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1942. Min Act: -0.0001

Data Index: 282281 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1891. Min Act: -0.0000

Data Index: 6157 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1885. Min Act: -0.0001

Data Index: 30112 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1950. Min Act: -0.0001

Data Index: 946042 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1265114 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1994. Min Act: -0.0001

Data Index: 425973 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1846. Min Act: -0.0001

Data Index: 879354 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1970. Min Act: -0.0000

Data Index: 578399 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1890. Min Act: -0.0000

Data Index: 165328 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1728. Min Act: -0.0000

Data Index: 734943 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.3284. Min Range: -0.3284

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1287298 (C4 (Web Text))

Max Activating Token Index: 233