Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3806 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0967. Min Range: -1.0967

Max Act: 1.0967. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1337307 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1409064 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4655. Min Act: -0.0000

Data Index: 79244 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4541. Min Act: -0.0000

Data Index: 744520 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4312. Min Act: -0.0000

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4478. Min Act: -0.0000

Data Index: 452838 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1274904 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1609657 (Python Code)

Max Activating Token Index: 830

Text #11

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1553317 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1629171 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4137. Min Act: -0.0000

Data Index: 508238 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4076. Min Act: -0.0000

Data Index: 271478 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.4307. Min Act: -0.0000

Data Index: 544929 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.3594. Min Act: -0.0000

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.3399. Min Act: -0.0000

Data Index: 901896 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.3093. Min Act: -0.0000

Data Index: 766359 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.0967. Min Range: -1.0967

Max Act: 0.3573. Min Act: -0.0000

Data Index: 547355 (C4 (Web Text))

Max Activating Token Index: 608