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

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

Neuron 3657 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.3495. Min Act: -0.0000

Data Index: 703321 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 5.3495. Min Range: -5.3495

Max Act: 4.1825. Min Act: -0.0000

Data Index: 748198 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 5.3495. Min Range: -5.3495

Max Act: 4.0818. Min Act: -0.0000

Data Index: 240444 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.7411. Min Act: -0.0000

Data Index: 843035 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.6150. Min Act: -0.0000

Data Index: 855247 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.6042. Min Act: -0.0000

Data Index: 330016 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.5900. Min Act: -0.0000

Data Index: 567813 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.4147. Min Act: -0.0000

Data Index: 102878 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.3848. Min Act: -0.0000

Data Index: 965806 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.3203. Min Act: -0.0000

Data Index: 851892 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.1225. Min Act: -0.0000

Data Index: 262489 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.1275. Min Act: -0.0000

Data Index: 1343119 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.1004. Min Act: -0.0000

Data Index: 421143 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 5.3495. Min Range: -5.3495

Max Act: 3.1341. Min Act: -0.0000

Data Index: 392666 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 5.3495. Min Range: -5.3495

Max Act: 2.9391. Min Act: -0.0000

Data Index: 1106606 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 5.3495. Min Range: -5.3495

Max Act: 2.8909. Min Act: -0.0000

Data Index: 825284 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 5.3495. Min Range: -5.3495

Max Act: 2.8814. Min Act: -0.0000

Data Index: 773094 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 5.3495. Min Range: -5.3495

Max Act: 2.8485. Min Act: -0.0000

Data Index: 150735 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 5.3495. Min Range: -5.3495

Max Act: 2.8293. Min Act: -0.0000

Data Index: 1028509 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 5.3495. Min Range: -5.3495

Max Act: 2.6920. Min Act: -0.0000

Data Index: 287243 (C4 (Web Text))

Max Activating Token Index: 845