Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1091. Min Act: -0.0001

Data Index: 455575 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0986. Min Act: -0.0001

Data Index: 923867 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1304663 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0948. Min Act: -0.0001

Data Index: 957799 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1120213 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1218849 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1050259 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0900. Min Act: -0.0001

Data Index: 756205 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0893. Min Act: -0.0001

Data Index: 171229 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1143314 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0843. Min Act: -0.0001

Data Index: 198874 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0874. Min Act: -0.0001

Data Index: 735827 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0868. Min Act: -0.0001

Data Index: 734088 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0866. Min Act: -0.0001

Data Index: 48597 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0807. Min Act: -0.0001

Data Index: 908008 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0801. Min Act: -0.0001

Data Index: 953701 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1127811 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1044432 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0821. Min Act: -0.0001

Data Index: 913428 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0819. Min Act: -0.0001

Data Index: 319105 (C4 (Web Text))

Max Activating Token Index: 1021