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

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

Neuron 2986 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1611509 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.3031. Min Act: -0.0001

Data Index: 1524246 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1495310 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1589114 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.3253. Min Act: -0.0001

Data Index: 1485469 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2904. Min Act: -0.0001

Data Index: 1628915 (Python Code)

Max Activating Token Index: 1003

Text #6

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1499513 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1590182 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1567895 (Python Code)

Max Activating Token Index: 965

Text #9

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1636888 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1624454 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1610432 (Python Code)

Max Activating Token Index: 810

Text #12

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1416280 (Python Code)

Max Activating Token Index: 720

Text #13

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1553345 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1519759 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1419047 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1609499 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2451. Min Act: -0.0001

Data Index: 1492290 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1535076 (Python Code)

Max Activating Token Index: 389

Text #19

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1393280 (Python Code)

Max Activating Token Index: 815