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

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

Neuron 3870 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1252. Min Range: -4.1252

Max Act: 3.9598. Min Act: -0.0000

Data Index: 196813 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 4.1252. Min Range: -4.1252

Max Act: 4.1252. Min Act: -0.0000

Data Index: 976162 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 4.1252. Min Range: -4.1252

Max Act: 3.9194. Min Act: -0.0000

Data Index: 365323 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 4.1252. Min Range: -4.1252

Max Act: 3.6575. Min Act: 0.0000

Data Index: 681441 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 4.1252. Min Range: -4.1252

Max Act: 3.3146. Min Act: -0.0000

Data Index: 1418451 (Python Code)

Max Activating Token Index: 526

Text #5

Max Range: 4.1252. Min Range: -4.1252

Max Act: 3.3332. Min Act: -0.0000

Data Index: 1186452 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.9807. Min Act: -0.0000

Data Index: 1147221 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 4.1252. Min Range: -4.1252

Max Act: 3.1362. Min Act: -0.0000

Data Index: 865314 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.6736. Min Act: -0.0000

Data Index: 289518 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.6604. Min Act: -0.0000

Data Index: 1184325 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.9245. Min Act: -0.0000

Data Index: 921632 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.7942. Min Act: -0.0000

Data Index: 816473 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.6021. Min Act: -0.0000

Data Index: 655536 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.6357. Min Act: -0.0000

Data Index: 1017267 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.5858. Min Act: -0.0000

Data Index: 1115376 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.5407. Min Act: -0.0000

Data Index: 632583 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.5284. Min Act: -0.0000

Data Index: 941661 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.6277. Min Act: -0.0000

Data Index: 1205381 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.6091. Min Act: -0.0000

Data Index: 528662 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 4.1252. Min Range: -4.1252

Max Act: 2.5663. Min Act: -0.0000

Data Index: 710448 (C4 (Web Text))

Max Activating Token Index: 1021