Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1709 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.9200. Min Act: -0.0001

Data Index: 593715 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.8867. Min Act: -0.0001

Data Index: 1238686 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.7212. Min Act: -0.0001

Data Index: 148715 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.7989. Min Act: -0.0001

Data Index: 14624 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.6732. Min Act: -0.0001

Data Index: 1202798 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5036. Min Act: -0.0001

Data Index: 1161925 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.6003. Min Act: -0.0001

Data Index: 674719 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5868. Min Act: -0.0001

Data Index: 954885 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.6097. Min Act: -0.0001

Data Index: 100926 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5958. Min Act: -0.0001

Data Index: 208459 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.6483. Min Act: -0.0001

Data Index: 1242665 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.8366. Min Act: -0.0001

Data Index: 876806 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5864. Min Act: -0.0001

Data Index: 934134 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.4859. Min Act: -0.0001

Data Index: 1194678 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5634. Min Act: -0.0001

Data Index: 958747 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5511. Min Act: -0.0001

Data Index: 640096 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.4171. Min Act: -0.0001

Data Index: 299253 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.5383. Min Act: -0.0001

Data Index: 1142641 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.3724. Min Act: -0.0001

Data Index: 1342207 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.9200. Min Range: -1.9200

Max Act: 1.4067. Min Act: -0.0001

Data Index: 273901 (C4 (Web Text))

Max Activating Token Index: 294