Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4193 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2081. Min Range: -3.2081

Max Act: 3.2081. Min Act: -0.0000

Data Index: 1038159 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.7276. Min Act: -0.0000

Data Index: 1643385 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.7451. Min Act: -0.0000

Data Index: 347182 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.7164. Min Act: -0.0000

Data Index: 1102602 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.5177. Min Act: -0.0000

Data Index: 982053 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.4557. Min Act: -0.0000

Data Index: 980961 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.4580. Min Act: -0.0000

Data Index: 1340736 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.5544. Min Act: -0.0000

Data Index: 42398 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1353971 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.3988. Min Act: -0.0000

Data Index: 387605 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.5294. Min Act: -0.0000

Data Index: 517847 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.3559. Min Act: -0.0000

Data Index: 1243775 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.3342. Min Act: -0.0000

Data Index: 39750 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.4121. Min Act: -0.0000

Data Index: 924352 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.2786. Min Act: -0.0000

Data Index: 54355 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.3595. Min Act: -0.0000

Data Index: 331157 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.2313. Min Act: -0.0000

Data Index: 507202 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.2311. Min Act: -0.0000

Data Index: 599874 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.2109. Min Act: -0.0000

Data Index: 160052 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 3.2081. Min Range: -3.2081

Max Act: 2.1996. Min Act: -0.0000

Data Index: 283999 (C4 (Web Text))

Max Activating Token Index: 97