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

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

Neuron 198 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: 1.9008. Min Range: -1.9008

Max Act: 1.9008. Min Act: -0.0002

Data Index: 881385 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.8437. Min Act: -0.0002

Data Index: 709457 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.7249. Min Act: -0.0002

Data Index: 1263816 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.6635. Min Act: -0.0002

Data Index: 226351 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.6085. Min Act: -0.0003

Data Index: 36123 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5798. Min Act: -0.0002

Data Index: 683914 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5634. Min Act: -0.0002

Data Index: 1258249 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5615. Min Act: -0.0002

Data Index: 225788 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5173. Min Act: -0.0002

Data Index: 24696 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5392. Min Act: -0.0002

Data Index: 552670 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5181. Min Act: -0.0002

Data Index: 957883 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5064. Min Act: -0.0002

Data Index: 1072171 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.5380. Min Act: -0.0002

Data Index: 33586 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4573. Min Act: -0.0002

Data Index: 927696 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4867. Min Act: -0.0002

Data Index: 1294812 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4808. Min Act: -0.0002

Data Index: 613159 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4215. Min Act: -0.0002

Data Index: 386620 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4027. Min Act: -0.0003

Data Index: 163398 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4300. Min Act: -0.0002

Data Index: 595212 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.9008. Min Range: -1.9008

Max Act: 1.4357. Min Act: -0.0002

Data Index: 1275430 (C4 (Web Text))

Max Activating Token Index: 211