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

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

Neuron 4806 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1263204 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3227. Min Act: -0.0000

Data Index: 262198 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1153379 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2340. Min Act: -0.0000

Data Index: 610473 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.0843. Min Act: -0.0000

Data Index: 680010 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1086508 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.0959. Min Act: -0.0000

Data Index: 341340 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.9105. Min Act: -0.0000

Data Index: 309954 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.7396. Min Act: -0.0000

Data Index: 430314 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.7001. Min Act: -0.0000

Data Index: 77237 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.6804. Min Act: -0.0000

Data Index: 346465 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.6403. Min Act: -0.0000

Data Index: 853319 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5892. Min Act: -0.0000

Data Index: 598486 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.6161. Min Act: -0.0000

Data Index: 893185 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5504. Min Act: -0.0000

Data Index: 582344 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5519. Min Act: -0.0000

Data Index: 484475 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1107739 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5747. Min Act: -0.0000

Data Index: 880165 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1321451 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.5865. Min Range: -1.5865

Max Act: 0.5538. Min Act: -0.0000

Data Index: 447317 (C4 (Web Text))

Max Activating Token Index: 86