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

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

Neuron 1016 in Layer 0

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: 1.4136. Min Range: -1.4136

Max Act: 1.4136. Min Act: -0.0001

Data Index: 636400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.2670. Min Act: -0.0001

Data Index: 748804 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.0996. Min Act: -0.0001

Data Index: 245946 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.1129. Min Act: -0.0001

Data Index: 318438 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.0633. Min Act: -0.0001

Data Index: 102618 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.0870. Min Act: -0.0001

Data Index: 1307331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.0876. Min Act: -0.0001

Data Index: 515808 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.0110. Min Act: -0.0001

Data Index: 491326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1151499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9825. Min Act: -0.0001

Data Index: 8865 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1035175 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.4136. Min Range: -1.4136

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1202245 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9791. Min Act: -0.0001

Data Index: 704475 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9477. Min Act: -0.0001

Data Index: 27128 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9430. Min Act: -0.0001

Data Index: 1175010 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9453. Min Act: -0.0001

Data Index: 1227743 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9476. Min Act: -0.0001

Data Index: 415221 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9405. Min Act: -0.0001

Data Index: 124226 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9387. Min Act: -0.0001

Data Index: 664916 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.4136. Min Range: -1.4136

Max Act: 0.9318. Min Act: -0.0001

Data Index: 324639 (C4 (Web Text))

Max Activating Token Index: 520