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

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

Neuron 4006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1132769 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.8449. Min Act: -0.0000

Data Index: 645085 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1073532 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.8055. Min Act: -0.0000

Data Index: 199168 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7134. Min Act: -0.0000

Data Index: 221172 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7653. Min Act: -0.0000

Data Index: 513942 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7174. Min Act: -0.0000

Data Index: 292438 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7412. Min Act: -0.0000

Data Index: 942415 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7848. Min Act: -0.0000

Data Index: 489651 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7156. Min Act: 0.0000

Data Index: 873661 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6828. Min Act: -0.0001

Data Index: 315982 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.7455. Min Act: -0.0001

Data Index: 981687 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6989. Min Act: -0.0000

Data Index: 404831 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6816. Min Act: -0.0001

Data Index: 166962 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6855. Min Act: -0.0001

Data Index: 875206 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1045804 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6370. Min Act: -0.0001

Data Index: 696959 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6550. Min Act: -0.0000

Data Index: 924457 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6283. Min Act: -0.0001

Data Index: 842354 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.8449. Min Range: -0.8449

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1017870 (C4 (Web Text))

Max Activating Token Index: 878