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

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

Neuron 5825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0000

Data Index: 319668 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1257347 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1342. Min Act: -0.0000

Data Index: 921858 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1318. Min Act: -0.0000

Data Index: 50157 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1221. Min Act: -0.0001

Data Index: 679033 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1119. Min Act: -0.0000

Data Index: 360120 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1300343 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1210. Min Act: -0.0000

Data Index: 921278 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1153. Min Act: -0.0000

Data Index: 726129 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1164. Min Act: -0.0000

Data Index: 413319 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1107. Min Act: -0.0000

Data Index: 415106 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1143. Min Act: -0.0000

Data Index: 559827 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1334323 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1021. Min Act: -0.0000

Data Index: 287998 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0973. Min Act: -0.0000

Data Index: 901945 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1008. Min Act: -0.0000

Data Index: 87428 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0997. Min Act: -0.0000

Data Index: 49464 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1055627 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0988. Min Act: -0.0000

Data Index: 676865 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0985. Min Act: -0.0000

Data Index: 320114 (C4 (Web Text))

Max Activating Token Index: 590