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

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

Neuron 3096 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: 0.6852. Min Range: -0.6852

Max Act: 0.6852. Min Act: -0.0000

Data Index: 474904 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.6590. Min Act: -0.0000

Data Index: 790242 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5895. Min Act: -0.0000

Data Index: 662120 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5422. Min Act: -0.0000

Data Index: 694526 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5929. Min Act: -0.0000

Data Index: 810072 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1081963 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5323. Min Act: -0.0000

Data Index: 610820 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4920. Min Act: -0.0000

Data Index: 425613 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1276345 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5257. Min Act: -0.0000

Data Index: 440379 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4789. Min Act: -0.0000

Data Index: 823317 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5150. Min Act: -0.0000

Data Index: 379055 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4853. Min Act: -0.0000

Data Index: 53883 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1258724 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4901. Min Act: -0.0000

Data Index: 500325 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4763. Min Act: -0.0000

Data Index: 979845 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4874. Min Act: -0.0000

Data Index: 265247 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4186. Min Act: -0.0000

Data Index: 366185 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4617. Min Act: -0.0000

Data Index: 517044 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.6852. Min Range: -0.6852

Max Act: 0.4477. Min Act: -0.0000

Data Index: 455553 (C4 (Web Text))

Max Activating Token Index: 655