Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3408 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0100. Min Act: -0.0002

Data Index: 870769 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0098. Min Act: -0.0002

Data Index: 223660 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1197353 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0095. Min Act: -0.0002

Data Index: 945833 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0096. Min Act: -0.0002

Data Index: 859694 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0094. Min Act: -0.0002

Data Index: 498819 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0094. Min Act: -0.0002

Data Index: 388234 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0093. Min Act: -0.0002

Data Index: 858401 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0092. Min Act: -0.0002

Data Index: 913278 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0091. Min Act: -0.0002

Data Index: 863330 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0090. Min Act: -0.0002

Data Index: 964226 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1213761 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0089. Min Act: -0.0002

Data Index: 891452 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0088. Min Act: -0.0002

Data Index: 687730 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0002

Data Index: 420031 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0088. Min Act: -0.0002

Data Index: 588608 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0089. Min Act: -0.0002

Data Index: 877426 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1287669 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0087. Min Act: -0.0002

Data Index: 571490 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0100. Min Range: -0.0100

Max Act: 0.0085. Min Act: -0.0002

Data Index: 755655 (C4 (Web Text))

Max Activating Token Index: 932