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

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

Neuron 2855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5274. Min Act: -0.0002

Data Index: 462270 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5548. Min Act: -0.0002

Data Index: 59151 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5307. Min Act: -0.0002

Data Index: 418390 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5181. Min Act: -0.0002

Data Index: 912975 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5190. Min Act: -0.0002

Data Index: 786068 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5197. Min Act: -0.0002

Data Index: 75959 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5241. Min Act: -0.0002

Data Index: 15467 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5071. Min Act: -0.0002

Data Index: 295998 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5031. Min Act: -0.0002

Data Index: 232580 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4881. Min Act: -0.0002

Data Index: 1166251 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5029. Min Act: -0.0002

Data Index: 1341005 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5018. Min Act: -0.0002

Data Index: 389169 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5040. Min Act: -0.0002

Data Index: 724550 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5002. Min Act: -0.0002

Data Index: 162070 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4846. Min Act: -0.0002

Data Index: 805097 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5270. Min Act: -0.0002

Data Index: 434870 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4826. Min Act: -0.0002

Data Index: 1010249 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4832. Min Act: -0.0002

Data Index: 271520 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4791. Min Act: -0.0002

Data Index: 155189 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4636. Min Act: -0.0002

Data Index: 1241936 (C4 (Web Text))

Max Activating Token Index: 710