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

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

Neuron 999 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: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 253553 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1430526 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1534114 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2734. Min Act: -0.0001

Data Index: 1626589 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2730. Min Act: -0.0001

Data Index: 445904 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1430022 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2805. Min Act: -0.0001

Data Index: 691696 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1378653 (Python Code)

Max Activating Token Index: 936

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1423845 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1431678 (Python Code)

Max Activating Token Index: 800

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1563797 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2145. Min Act: -0.0000

Data Index: 295484 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1399800 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1572042 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1431170 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1550843 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1378357 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2250. Min Act: -0.0000

Data Index: 432689 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2014. Min Act: -0.0000

Data Index: 298306 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1388850 (Python Code)

Max Activating Token Index: 681