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

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

Neuron 2036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0069. Min Range: -1.0069

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1331522 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1323891 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1009962 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1153751 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8813. Min Act: -0.0000

Data Index: 478258 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9029. Min Act: -0.0001

Data Index: 840890 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.9029. Min Act: -0.0001

Data Index: 106341 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8664. Min Act: -0.0001

Data Index: 315465 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8571. Min Act: -0.0000

Data Index: 257834 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8429. Min Act: -0.0001

Data Index: 42882 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8380. Min Act: -0.0000

Data Index: 108804 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8591. Min Act: -0.0001

Data Index: 26701 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8291. Min Act: -0.0000

Data Index: 981641 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8162. Min Act: -0.0001

Data Index: 97330 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.8301. Min Act: -0.0001

Data Index: 641155 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7885. Min Act: -0.0001

Data Index: 241370 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7535. Min Act: -0.0001

Data Index: 315405 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7936. Min Act: -0.0000

Data Index: 228883 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7867. Min Act: -0.0001

Data Index: 1162754 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.0069. Min Range: -1.0069

Max Act: 0.7007. Min Act: -0.0001

Data Index: 474747 (C4 (Web Text))

Max Activating Token Index: 337