Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1493 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.5135. Min Act: -0.0001

Data Index: 1290151 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.3507. Min Act: -0.0001

Data Index: 386015 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2237. Min Act: -0.0001

Data Index: 563160 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1083983 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1101618 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2672. Min Act: -0.0001

Data Index: 414840 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2634. Min Act: -0.0001

Data Index: 1046495 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.3161. Min Act: -0.0001

Data Index: 231243 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2055. Min Act: -0.0001

Data Index: 596138 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1151659 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2587. Min Act: -0.0001

Data Index: 188055 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1142073 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1176885 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2171. Min Act: -0.0001

Data Index: 5061 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2278. Min Act: -0.0001

Data Index: 672723 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2171. Min Act: -0.0001

Data Index: 456639 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.1743. Min Act: -0.0001

Data Index: 10369 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.2269. Min Act: -0.0001

Data Index: 234693 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.1965. Min Act: -0.0001

Data Index: 612654 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.5135. Min Range: -0.5135

Max Act: 0.1899. Min Act: -0.0001

Data Index: 467484 (C4 (Web Text))

Max Activating Token Index: 243