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

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

Neuron 4025 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: 2.2764. Min Range: -2.2764

Max Act: 2.2431. Min Act: -0.0002

Data Index: 1341233 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.2764. Min Act: -0.0002

Data Index: 67263 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.2387. Min Act: -0.0002

Data Index: 1277495 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.1842. Min Act: -0.0002

Data Index: 425911 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.2107. Min Act: -0.0002

Data Index: 344188 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.1321. Min Act: -0.0002

Data Index: 775285 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.1033. Min Act: -0.0002

Data Index: 760195 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0581. Min Act: -0.0002

Data Index: 1237259 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.1559. Min Act: -0.0002

Data Index: 60227 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0596. Min Act: -0.0002

Data Index: 861348 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.1220. Min Act: -0.0002

Data Index: 1093981 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0711. Min Act: -0.0002

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0581. Min Act: -0.0003

Data Index: 601442 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.1019. Min Act: -0.0002

Data Index: 1001233 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.2764. Min Range: -2.2764

Max Act: 1.9948. Min Act: -0.0002

Data Index: 968143 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0772. Min Act: -0.0002

Data Index: 46118 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0592. Min Act: -0.0002

Data Index: 347756 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 2.2764. Min Range: -2.2764

Max Act: 2.0176. Min Act: -0.0002

Data Index: 575325 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 2.2764. Min Range: -2.2764

Max Act: 1.9691. Min Act: -0.0002

Data Index: 120055 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.2764. Min Range: -2.2764

Max Act: 1.9864. Min Act: -0.0002

Data Index: 202576 (C4 (Web Text))

Max Activating Token Index: 14