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

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

Neuron 2471 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8269. Min Act: 0.0000

Data Index: 1098194 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8523. Min Act: -0.0000

Data Index: 276071 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1155590 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7773. Min Act: -0.0000

Data Index: 487849 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7703. Min Act: -0.0000

Data Index: 759975 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7447. Min Act: -0.0000

Data Index: 670711 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7154. Min Act: -0.0000

Data Index: 863928 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7131. Min Act: -0.0000

Data Index: 217631 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6926. Min Act: -0.0000

Data Index: 607121 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6739. Min Act: 0.0000

Data Index: 766059 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6955. Min Act: -0.0000

Data Index: 146667 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6619. Min Act: -0.0000

Data Index: 162024 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6809. Min Act: -0.0000

Data Index: 169367 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1045483 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6746. Min Act: -0.0001

Data Index: 595373 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1062968 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6472. Min Act: -0.0001

Data Index: 235507 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6690. Min Act: -0.0000

Data Index: 666053 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1148891 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6302. Min Act: -0.0001

Data Index: 392443 (C4 (Web Text))

Max Activating Token Index: 909