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

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

Neuron 1672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1631192 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1362003 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.6355. Min Act: -0.0000

Data Index: 1276324 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7231. Min Act: -0.0000

Data Index: 75970 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.5577. Min Act: -0.0000

Data Index: 633236 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1404883 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.6187. Min Act: -0.0001

Data Index: 1550200 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.6022. Min Act: -0.0000

Data Index: 265758 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1587977 (Python Code)

Max Activating Token Index: 167

Text #9

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4344. Min Act: -0.0000

Data Index: 618008 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.5694. Min Act: -0.0000

Data Index: 689753 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1452225 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1496245 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1477203 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4666. Min Act: -0.0000

Data Index: 994606 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1232327 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4196. Min Act: -0.0000

Data Index: 448255 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.3942. Min Act: -0.0000

Data Index: 166090 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4035. Min Act: -0.0000

Data Index: 911415 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.4422. Min Act: -0.0000

Data Index: 354845 (C4 (Web Text))

Max Activating Token Index: 932