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

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

Neuron 2013 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: 2.8583. Min Range: -2.8583

Max Act: 2.8583. Min Act: -0.0000

Data Index: 1093954 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.5028. Min Act: -0.0000

Data Index: 633666 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.4917. Min Act: -0.0000

Data Index: 1232595 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.3654. Min Act: -0.0000

Data Index: 522607 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.2474. Min Act: -0.0000

Data Index: 1050189 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.2988. Min Act: -0.0000

Data Index: 923310 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.3058. Min Act: 0.0000

Data Index: 1113950 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1168249 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.0632. Min Act: -0.0000

Data Index: 270408 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.8998. Min Act: -0.0000

Data Index: 1215092 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 2.8583. Min Range: -2.8583

Max Act: 2.0511. Min Act: -0.0000

Data Index: 1005617 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.8910. Min Act: -0.0000

Data Index: 1157597 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.7361. Min Act: -0.0000

Data Index: 1081042 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.7272. Min Act: -0.0000

Data Index: 1122121 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1433705 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.5999. Min Act: -0.0000

Data Index: 312875 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.4969. Min Act: -0.0000

Data Index: 781416 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.5224. Min Act: -0.0000

Data Index: 28292 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1063932 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 2.8583. Min Range: -2.8583

Max Act: 1.6950. Min Act: -0.0000

Data Index: 164937 (C4 (Web Text))

Max Activating Token Index: 216