Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.6163. Min Act: -0.0000

Data Index: 547697 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5804. Min Act: -0.0000

Data Index: 314122 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4874. Min Act: -0.0000

Data Index: 526166 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5239. Min Act: -0.0000

Data Index: 244522 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5253. Min Act: -0.0000

Data Index: 853172 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5431. Min Act: -0.0000

Data Index: 151057 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1137977 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5194. Min Act: -0.0000

Data Index: 953503 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5015. Min Act: -0.0001

Data Index: 250736 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.3864. Min Act: -0.0000

Data Index: 694365 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4984. Min Act: -0.0000

Data Index: 284553 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1107029 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5285. Min Act: -0.0000

Data Index: 239894 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1291253 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4600. Min Act: -0.0000

Data Index: 420722 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1022321 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.5108. Min Act: -0.0000

Data Index: 792028 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1297627 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4387. Min Act: -0.0000

Data Index: 642770 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.6163. Min Range: -0.6163

Max Act: 0.4534. Min Act: -0.0000

Data Index: 324857 (C4 (Web Text))

Max Activating Token Index: 40