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

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

Neuron 2432 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1208410 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.8012. Min Act: -0.0000

Data Index: 749356 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6981. Min Act: -0.0000

Data Index: 300733 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6685. Min Act: -0.0000

Data Index: 714599 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6431. Min Act: -0.0000

Data Index: 498877 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6244. Min Act: -0.0000

Data Index: 133923 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6608. Min Act: -0.0000

Data Index: 207093 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6027. Min Act: -0.0000

Data Index: 701455 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1278217 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5791. Min Act: -0.0000

Data Index: 382443 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5669. Min Act: -0.0000

Data Index: 4958 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5714. Min Act: -0.0000

Data Index: 308151 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5375. Min Act: -0.0000

Data Index: 147216 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5084. Min Act: -0.0000

Data Index: 6512 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5043. Min Act: -0.0000

Data Index: 309267 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5320. Min Act: -0.0000

Data Index: 485801 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1285510 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5147. Min Act: -0.0000

Data Index: 48615 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4962. Min Act: -0.0000

Data Index: 100576 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1294871 (C4 (Web Text))

Max Activating Token Index: 387