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

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

Neuron 114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1126. Min Act: -0.0000

Data Index: 757286 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1097. Min Act: -0.0001

Data Index: 768517 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1093000 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1025. Min Act: -0.0000

Data Index: 876781 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0993. Min Act: -0.0000

Data Index: 73793 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1054. Min Act: -0.0001

Data Index: 212008 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0944. Min Act: -0.0000

Data Index: 270053 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0977. Min Act: -0.0000

Data Index: 259253 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0924. Min Act: -0.0001

Data Index: 557762 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1330604 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0900. Min Act: -0.0001

Data Index: 709119 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0893. Min Act: -0.0001

Data Index: 880891 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0918. Min Act: -0.0001

Data Index: 877925 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1294491 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0906. Min Act: -0.0001

Data Index: 282879 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0861. Min Act: -0.0001

Data Index: 469245 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0868. Min Act: -0.0001

Data Index: 973135 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0851. Min Act: -0.0001

Data Index: 806337 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1480337 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1275625 (C4 (Web Text))

Max Activating Token Index: 326