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

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

Neuron 4516 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 397834 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 789203 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 678310 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 492374 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1299620 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 447136 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 726786 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 624193 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1244977 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 247611 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 262456 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 910788 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 7832 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1205234 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1506105 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 47322 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1090789 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1307961 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 248027 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1281543 (C4 (Web Text))

Max Activating Token Index: 940