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

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

Neuron 1312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.6618. Min Act: -0.0002

Data Index: 795059 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4979. Min Act: -0.0002

Data Index: 641349 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4979. Min Act: -0.0002

Data Index: 663931 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.5996. Min Act: -0.0002

Data Index: 84998 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4850. Min Act: -0.0002

Data Index: 1436839 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.5907. Min Act: -0.0002

Data Index: 1556136 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.5088. Min Act: -0.0002

Data Index: 1402675 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4161. Min Act: -0.0002

Data Index: 1418536 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.6082. Min Act: -0.0002

Data Index: 1640297 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4797. Min Act: -0.0002

Data Index: 1298846 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.3691. Min Act: -0.0002

Data Index: 1583673 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.2595. Min Act: -0.0002

Data Index: 1564283 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4761. Min Act: -0.0002

Data Index: 402159 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4584. Min Act: -0.0002

Data Index: 1314971 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4150. Min Act: -0.0002

Data Index: 1594938 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4517. Min Act: -0.0002

Data Index: 577841 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4482. Min Act: -0.0002

Data Index: 390279 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.5780. Min Act: -0.0002

Data Index: 618528 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.3848. Min Act: -0.0002

Data Index: 1504442 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 2.6618. Min Range: -2.6618

Max Act: 2.4642. Min Act: -0.0002

Data Index: 1463639 (Python Code)

Max Activating Token Index: 267