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

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

Neuron 2458 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0003

Data Index: 702739 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0449. Min Act: -0.0003

Data Index: 678958 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0443. Min Act: -0.0003

Data Index: 633497 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1004757 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1318410 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1330307 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0425. Min Act: -0.0003

Data Index: 210737 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0407. Min Act: -0.0003

Data Index: 644918 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1038752 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1101000 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0424. Min Act: -0.0003

Data Index: 974305 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0400. Min Act: -0.0003

Data Index: 961550 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0399. Min Act: -0.0003

Data Index: 604524 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1194328 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1106549 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1149656 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0407. Min Act: -0.0003

Data Index: 916153 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0387. Min Act: -0.0003

Data Index: 881368 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0386. Min Act: -0.0003

Data Index: 464510 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1064475 (C4 (Web Text))

Max Activating Token Index: 397