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

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

Neuron 2536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1258972 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0433. Min Act: -0.0002

Data Index: 496202 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0484. Min Act: -0.0002

Data Index: 314274 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0457. Min Act: -0.0002

Data Index: 753189 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0486. Min Act: -0.0001

Data Index: 955138 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0460. Min Act: -0.0002

Data Index: 665783 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1354464 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0426. Min Act: -0.0002

Data Index: 520848 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1164266 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1099859 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0422. Min Act: -0.0002

Data Index: 930065 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1131534 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0416. Min Act: -0.0001

Data Index: 369065 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1161323 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0402. Min Act: -0.0001

Data Index: 416131 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0414. Min Act: -0.0001

Data Index: 912707 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1340033 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0414. Min Act: -0.0002

Data Index: 843820 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0379. Min Act: -0.0001

Data Index: 858426 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.0502. Min Range: -0.0502

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1304796 (C4 (Web Text))

Max Activating Token Index: 722