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

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

Neuron 568 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0029. Min Range: -2.0029

Max Act: 2.0024. Min Act: -0.0001

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9083. Min Act: -0.0001

Data Index: 334779 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9600. Min Act: -0.0001

Data Index: 1338955 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9766. Min Act: -0.0001

Data Index: 250634 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8003. Min Act: -0.0001

Data Index: 1188939 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9215. Min Act: -0.0001

Data Index: 392358 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8731. Min Act: -0.0001

Data Index: 2524 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8166. Min Act: -0.0001

Data Index: 479687 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9082. Min Act: -0.0001

Data Index: 1250803 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9573. Min Act: -0.0001

Data Index: 595698 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8874. Min Act: -0.0001

Data Index: 1167282 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8981. Min Act: -0.0001

Data Index: 1147226 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 2.0029. Min Range: -2.0029

Max Act: 2.0029. Min Act: -0.0001

Data Index: 595440 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8779. Min Act: -0.0001

Data Index: 1003513 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9085. Min Act: -0.0001

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.9192. Min Act: -0.0001

Data Index: 909150 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8202. Min Act: -0.0001

Data Index: 901579 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8317. Min Act: -0.0001

Data Index: 809445 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.7874. Min Act: -0.0001

Data Index: 1225017 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 2.0029. Min Range: -2.0029

Max Act: 1.8309. Min Act: -0.0001

Data Index: 741239 (C4 (Web Text))

Max Activating Token Index: 386