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

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

Neuron 1723 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: 1.0045. Min Range: -1.0045

Max Act: 1.0045. Min Act: -0.0002

Data Index: 1229221 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9568. Min Act: -0.0002

Data Index: 410919 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9328. Min Act: -0.0002

Data Index: 1273306 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9270. Min Act: -0.0002

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9402. Min Act: -0.0003

Data Index: 880173 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9155. Min Act: -0.0003

Data Index: 955576 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9160. Min Act: -0.0002

Data Index: 448961 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8967. Min Act: -0.0002

Data Index: 463355 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9019. Min Act: -0.0002

Data Index: 1211044 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9115. Min Act: -0.0003

Data Index: 509684 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8979. Min Act: -0.0002

Data Index: 429459 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8929. Min Act: -0.0002

Data Index: 83268 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9119. Min Act: -0.0002

Data Index: 642973 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8850. Min Act: -0.0002

Data Index: 448555 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8910. Min Act: -0.0002

Data Index: 1216759 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8915. Min Act: -0.0002

Data Index: 439654 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8848. Min Act: -0.0002

Data Index: 825424 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9012. Min Act: -0.0002

Data Index: 1084950 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8773. Min Act: -0.0002

Data Index: 491325 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8857. Min Act: -0.0002

Data Index: 910363 (C4 (Web Text))

Max Activating Token Index: 635