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

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

Neuron 276 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.4267. Min Act: -0.0000

Data Index: 516305 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.4067. Min Act: -0.0000

Data Index: 528968 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3480. Min Act: 0.0000

Data Index: 732137 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3465. Min Act: 0.0000

Data Index: 1217658 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3409. Min Act: -0.0000

Data Index: 599478 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3375. Min Act: -0.0000

Data Index: 979437 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3183. Min Act: -0.0000

Data Index: 836733 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3197. Min Act: -0.0000

Data Index: 500628 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3056. Min Act: -0.0000

Data Index: 284810 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3074. Min Act: -0.0000

Data Index: 712505 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2946. Min Act: -0.0000

Data Index: 842446 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1277776 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3070. Min Act: -0.0000

Data Index: 888067 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2987. Min Act: -0.0000

Data Index: 994824 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2866. Min Act: -0.0000

Data Index: 594884 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.3042. Min Act: -0.0000

Data Index: 172992 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2931. Min Act: -0.0000

Data Index: 880251 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2947. Min Act: -0.0000

Data Index: 833172 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2899. Min Act: 0.0000

Data Index: 839436 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.4267. Min Range: -0.4267

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1132785 (C4 (Web Text))

Max Activating Token Index: 422