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

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

Neuron 1117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.6235. Min Act: -0.0004

Data Index: 786335 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5660. Min Act: -0.0004

Data Index: 444148 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4865. Min Act: -0.0004

Data Index: 483335 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5701. Min Act: -0.0004

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5792. Min Act: -0.0004

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5823. Min Act: -0.0004

Data Index: 184878 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4980. Min Act: -0.0004

Data Index: 1281791 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5403. Min Act: -0.0004

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4407. Min Act: -0.0004

Data Index: 483380 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4684. Min Act: -0.0004

Data Index: 1065158 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5058. Min Act: -0.0004

Data Index: 229112 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5340. Min Act: -0.0004

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5116. Min Act: -0.0004

Data Index: 486059 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4640. Min Act: -0.0004

Data Index: 709591 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.5085. Min Act: -0.0004

Data Index: 123365 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4602. Min Act: -0.0004

Data Index: 163747 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4723. Min Act: -0.0004

Data Index: 192750 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4410. Min Act: -0.0004

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4850. Min Act: -0.0004

Data Index: 89879 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.6235. Min Range: -0.6235

Max Act: 0.4568. Min Act: -0.0004

Data Index: 1358120 (C4 (Web Text))

Max Activating Token Index: 887