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

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

Neuron 1880 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5426. Min Act: -0.0001

Data Index: 551739 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.6152. Min Act: -0.0001

Data Index: 307867 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5144. Min Act: -0.0001

Data Index: 348447 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4261. Min Act: -0.0001

Data Index: 99756 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4238. Min Act: -0.0001

Data Index: 479107 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4353. Min Act: -0.0001

Data Index: 524264 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4133. Min Act: -0.0001

Data Index: 1186595 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3987. Min Act: -0.0001

Data Index: 342378 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1118113 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4017. Min Act: -0.0001

Data Index: 74820 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4008. Min Act: -0.0001

Data Index: 910431 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3582. Min Act: -0.0001

Data Index: 382142 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3697. Min Act: -0.0001

Data Index: 581169 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1208455 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3939. Min Act: -0.0001

Data Index: 688615 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4032. Min Act: -0.0001

Data Index: 796399 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1041331 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3757. Min Act: -0.0001

Data Index: 963245 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1320343 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3770. Min Act: -0.0001

Data Index: 17520 (C4 (Web Text))

Max Activating Token Index: 336