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

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

Neuron 3885 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1508552 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1612964 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1637917 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1442138 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1615181 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1585052 (Python Code)

Max Activating Token Index: 952

Text #6

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1547749 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1541906 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1601607 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1447543 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1445384 (Python Code)

Max Activating Token Index: 610

Text #11

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1471378 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1589940 (Python Code)

Max Activating Token Index: 697

Text #13

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3100. Min Act: -0.0000

Data Index: 742936 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1583416 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1456000 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1454584 (Python Code)

Max Activating Token Index: 840

Text #17

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1441821 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1629932 (Python Code)

Max Activating Token Index: 316

Text #19

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1527291 (Python Code)

Max Activating Token Index: 368