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

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

Neuron 2441 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: 0.7593. Min Range: -0.7593

Max Act: 0.7593. Min Act: -0.0000

Data Index: 102371 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6940. Min Act: -0.0000

Data Index: 853115 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6801. Min Act: -0.0000

Data Index: 240332 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6378. Min Act: -0.0000

Data Index: 288365 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1125878 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6320. Min Act: -0.0000

Data Index: 825935 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.6165. Min Act: -0.0000

Data Index: 562315 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5899. Min Act: -0.0000

Data Index: 171910 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5855. Min Act: -0.0000

Data Index: 33740 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5446. Min Act: 0.0000

Data Index: 51888 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5073. Min Act: 0.0000

Data Index: 154589 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1061811 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4978. Min Act: -0.0000

Data Index: 395806 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4806. Min Act: -0.0000

Data Index: 749483 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5016. Min Act: -0.0000

Data Index: 559192 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4851. Min Act: 0.0000

Data Index: 465165 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.5125. Min Act: -0.0000

Data Index: 728222 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4931. Min Act: 0.0000

Data Index: 471432 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4821. Min Act: 0.0000

Data Index: 925694 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.7593. Min Range: -0.7593

Max Act: 0.4761. Min Act: 0.0000

Data Index: 1074637 (C4 (Web Text))

Max Activating Token Index: 514