Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 352 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.3766. Min Act: -0.0001

Data Index: 1391239 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.3511. Min Act: -0.0001

Data Index: 1506703 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.3788. Min Act: -0.0001

Data Index: 1441344 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.3739. Min Act: -0.0001

Data Index: 1610477 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.1897. Min Act: -0.0001

Data Index: 1638421 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.3334. Min Act: -0.0001

Data Index: 1501281 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.4773. Min Act: -0.0001

Data Index: 1638344 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2603. Min Act: -0.0001

Data Index: 1479363 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.1017. Min Act: -0.0001

Data Index: 1397656 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0903. Min Act: -0.0001

Data Index: 1472478 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0773. Min Act: -0.0001

Data Index: 1459993 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0865. Min Act: -0.0001

Data Index: 1398649 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2262. Min Act: -0.0001

Data Index: 1489799 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0718. Min Act: -0.0001

Data Index: 1465064 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2056. Min Act: -0.0001

Data Index: 1492377 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2239. Min Act: -0.0001

Data Index: 1453048 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2145. Min Act: -0.0001

Data Index: 1457470 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.3588. Min Act: -0.0001

Data Index: 1538086 (Python Code)

Max Activating Token Index: 623

Text #18

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0670. Min Act: -0.0001

Data Index: 1510180 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0598. Min Act: -0.0001

Data Index: 1642803 (Python Code)

Max Activating Token Index: 774