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

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

Neuron 165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2287. Min Act: -0.0002

Data Index: 101477 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2193. Min Act: -0.0002

Data Index: 1268064 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2202. Min Act: -0.0002

Data Index: 1233855 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2104. Min Act: -0.0002

Data Index: 644386 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2087. Min Act: -0.0002

Data Index: 1160192 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2082. Min Act: -0.0002

Data Index: 627941 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2183. Min Act: -0.0002

Data Index: 909519 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2057. Min Act: -0.0002

Data Index: 1172861 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2049. Min Act: -0.0002

Data Index: 618972 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2006. Min Act: -0.0002

Data Index: 635729 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1987. Min Act: -0.0002

Data Index: 64932 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1987. Min Act: -0.0002

Data Index: 1031984 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1994. Min Act: -0.0002

Data Index: 747270 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1927. Min Act: -0.0002

Data Index: 1155277 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1978. Min Act: -0.0002

Data Index: 800233 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1948. Min Act: -0.0002

Data Index: 865147 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1887. Min Act: -0.0002

Data Index: 1057725 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1918. Min Act: -0.0002

Data Index: 1257723 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1920. Min Act: -0.0002

Data Index: 704513 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1866. Min Act: -0.0002

Data Index: 777256 (C4 (Web Text))

Max Activating Token Index: 208