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

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

Neuron 996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0001

Data Index: 448703 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1228. Min Act: -0.0001

Data Index: 244626 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1176. Min Act: -0.0001

Data Index: 341723 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1202. Min Act: -0.0001

Data Index: 153627 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1821 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1526078 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1164. Min Act: -0.0001

Data Index: 69956 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1091. Min Act: -0.0001

Data Index: 463183 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1160. Min Act: -0.0001

Data Index: 142408 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1607642 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1097. Min Act: -0.0001

Data Index: 63392 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1313520 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1108470 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1032. Min Act: -0.0001

Data Index: 940797 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1234216 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1055. Min Act: -0.0001

Data Index: 231816 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1056. Min Act: -0.0001

Data Index: 546728 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1240970 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1035. Min Act: -0.0001

Data Index: 566593 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1068045 (C4 (Web Text))

Max Activating Token Index: 91