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

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

Neuron 5835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.6031. Min Act: -0.0000

Data Index: 514555 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.6279. Min Act: 0.0000

Data Index: 817679 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1012384 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1317125 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5681. Min Act: -0.0000

Data Index: 394782 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5271. Min Act: 0.0000

Data Index: 30680 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5201. Min Act: -0.0000

Data Index: 596359 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5320. Min Act: 0.0000

Data Index: 141182 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5102. Min Act: 0.0000

Data Index: 345378 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.5129. Min Act: 0.0000

Data Index: 1114668 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4949. Min Act: -0.0000

Data Index: 746057 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4935. Min Act: -0.0000

Data Index: 230909 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1063237 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4866. Min Act: 0.0000

Data Index: 1269946 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4989. Min Act: 0.0000

Data Index: 520993 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4830. Min Act: -0.0000

Data Index: 290312 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4762. Min Act: -0.0000

Data Index: 882125 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4740. Min Act: -0.0000

Data Index: 96061 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1277056 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.6279. Min Range: -0.6279

Max Act: 0.4801. Min Act: -0.0000

Data Index: 891333 (C4 (Web Text))

Max Activating Token Index: 347