Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.3167. Min Act: -0.0001

Data Index: 610962 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.2353. Min Act: -0.0002

Data Index: 908717 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1014. Min Act: -0.0001

Data Index: 888164 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0355. Min Act: -0.0001

Data Index: 1169758 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0510. Min Act: -0.0001

Data Index: 535431 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0350. Min Act: -0.0002

Data Index: 925176 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0378. Min Act: -0.0001

Data Index: 996895 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0029. Min Act: -0.0002

Data Index: 150776 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9910. Min Act: -0.0002

Data Index: 865293 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9602. Min Act: -0.0001

Data Index: 947742 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9833. Min Act: -0.0001

Data Index: 329937 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0171. Min Act: -0.0002

Data Index: 534088 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9812. Min Act: -0.0001

Data Index: 115532 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9573. Min Act: -0.0001

Data Index: 1210775 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9779. Min Act: -0.0001

Data Index: 285998 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8400. Min Act: -0.0001

Data Index: 548203 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9633. Min Act: -0.0002

Data Index: 360195 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9424. Min Act: -0.0001

Data Index: 968136 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0197. Min Act: -0.0002

Data Index: 356711 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8942. Min Act: -0.0001

Data Index: 957859 (C4 (Web Text))

Max Activating Token Index: 229