Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.9586. Min Act: -0.0000

Data Index: 204165 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8748. Min Act: -0.0000

Data Index: 976950 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8416. Min Act: -0.0000

Data Index: 756 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1250221 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6854. Min Act: 0.0000

Data Index: 1282648 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6836. Min Act: -0.0000

Data Index: 671662 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6449. Min Act: -0.0000

Data Index: 202461 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6547. Min Act: -0.0001

Data Index: 748205 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6354. Min Act: -0.0000

Data Index: 191899 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1176501 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6460. Min Act: -0.0000

Data Index: 241693 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6006. Min Act: -0.0000

Data Index: 639686 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.5945. Min Act: -0.0000

Data Index: 688930 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6299. Min Act: -0.0000

Data Index: 794721 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1079747 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6021. Min Act: -0.0001

Data Index: 496848 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6136. Min Act: -0.0000

Data Index: 234908 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1278036 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.5884. Min Act: -0.0001

Data Index: 280445 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6024. Min Act: -0.0000

Data Index: 600247 (C4 (Web Text))

Max Activating Token Index: 741