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

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

Neuron 4600 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: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0002

Data Index: 470557 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0002

Data Index: 544276 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0002

Data Index: 438734 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0474. Min Act: -0.0002

Data Index: 750380 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1496669 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1536327 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 767198 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 927453 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 960061 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 996318 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 373947 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1171271 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1264286 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 198569 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1069219 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0462. Min Act: -0.0002

Data Index: 95671 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0433. Min Act: -0.0002

Data Index: 81632 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0432. Min Act: -0.0002

Data Index: 2372 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0432. Min Act: -0.0002

Data Index: 93041 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0432. Min Act: -0.0002

Data Index: 210546 (C4 (Web Text))

Max Activating Token Index: 1