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

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

Neuron 2672 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.8279. Min Act: -0.0000

Data Index: 195276 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1645027 (Python Code)

Max Activating Token Index: 586

Text #2

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1514548 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.5314. Min Act: -0.0000

Data Index: 329557 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.5268. Min Act: -0.0000

Data Index: 1620338 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1515302 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1611431 (Python Code)

Max Activating Token Index: 935

Text #7

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.5452. Min Act: -0.0000

Data Index: 1423449 (Python Code)

Max Activating Token Index: 604

Text #8

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1389049 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.5557. Min Act: -0.0000

Data Index: 1653013 (Python Code)

Max Activating Token Index: 920

Text #10

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1566456 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.6731. Min Act: -0.0000

Data Index: 1477004 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1388315 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1612260 (Python Code)

Max Activating Token Index: 526

Text #14

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1477332 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.3323. Min Act: -0.0000

Data Index: 652115 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.6009. Min Act: -0.0000

Data Index: 1593267 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1579467 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1656683 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 1.8279. Min Range: -1.8279

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1632318 (Python Code)

Max Activating Token Index: 213