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

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

Neuron 1442 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6737. Min Act: -0.0001

Data Index: 411139 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5705. Min Act: -0.0001

Data Index: 777688 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5715. Min Act: -0.0001

Data Index: 466314 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5610. Min Act: -0.0001

Data Index: 1319884 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5525. Min Act: -0.0001

Data Index: 980716 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5397. Min Act: -0.0001

Data Index: 580233 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5375. Min Act: -0.0001

Data Index: 842970 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5320. Min Act: -0.0001

Data Index: 236007 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5296. Min Act: -0.0001

Data Index: 1055958 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5566. Min Act: -0.0001

Data Index: 38723 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4792. Min Act: -0.0001

Data Index: 83119 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5172. Min Act: -0.0001

Data Index: 456129 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4968. Min Act: -0.0001

Data Index: 359568 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1181385 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5381. Min Act: -0.0001

Data Index: 945548 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4920. Min Act: -0.0001

Data Index: 41303 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5036. Min Act: -0.0001

Data Index: 636239 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1116643 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1257709 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4722. Min Act: -0.0001

Data Index: 44376 (C4 (Web Text))

Max Activating Token Index: 830