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

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

Neuron 5491 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1604950 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1580642 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3488. Min Act: -0.0001

Data Index: 1651000 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1648273 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1562322 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2911. Min Act: -0.0001

Data Index: 257121 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1456880 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2866. Min Act: -0.0001

Data Index: 797469 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1455195 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2639. Min Act: -0.0001

Data Index: 1640965 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2289. Min Act: -0.0001

Data Index: 30522 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2798. Min Act: -0.0001

Data Index: 987562 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1591896 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1163721 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2378. Min Act: -0.0001

Data Index: 320403 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1506720 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1642055 (Python Code)

Max Activating Token Index: 776

Text #17

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1589651 (Python Code)

Max Activating Token Index: 797

Text #18

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2469. Min Act: -0.0001

Data Index: 462568 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.3569. Min Range: -0.3569

Max Act: 0.2460. Min Act: -0.0001

Data Index: 595285 (C4 (Web Text))

Max Activating Token Index: 848