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

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

Neuron 4829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1008699 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0595. Min Act: -0.0002

Data Index: 946883 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0596. Min Act: -0.0002

Data Index: 469736 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0510. Min Act: -0.0002

Data Index: 311070 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0456. Min Act: -0.0002

Data Index: 813656 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0480. Min Act: -0.0002

Data Index: 69165 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0460. Min Act: -0.0002

Data Index: 585059 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1508282 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0450. Min Act: -0.0002

Data Index: 388547 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1072974 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1557478 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0464. Min Act: -0.0002

Data Index: 874912 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0445. Min Act: -0.0002

Data Index: 243712 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1212183 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0433. Min Act: -0.0002

Data Index: 409649 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1389760 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0430. Min Act: -0.0002

Data Index: 238405 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1618559 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0430. Min Act: -0.0002

Data Index: 42356 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1287874 (C4 (Web Text))

Max Activating Token Index: 566