Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 623 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.5994. Min Act: -0.0002

Data Index: 1091359 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.6092. Min Act: -0.0002

Data Index: 382936 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.5379. Min Act: -0.0002

Data Index: 706357 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4698. Min Act: -0.0002

Data Index: 987062 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4587. Min Act: -0.0002

Data Index: 1352054 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.5052. Min Act: -0.0002

Data Index: 871604 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4926. Min Act: -0.0002

Data Index: 330078 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4814. Min Act: -0.0002

Data Index: 846675 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4278. Min Act: -0.0002

Data Index: 506455 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4408. Min Act: -0.0002

Data Index: 215144 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4714. Min Act: -0.0001

Data Index: 611141 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4729. Min Act: -0.0001

Data Index: 1235514 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4676. Min Act: -0.0002

Data Index: 1018465 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4150. Min Act: -0.0002

Data Index: 1193583 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4177. Min Act: -0.0002

Data Index: 216414 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4577. Min Act: -0.0002

Data Index: 1236324 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4473. Min Act: -0.0002

Data Index: 238537 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4320. Min Act: -0.0002

Data Index: 733574 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4163. Min Act: -0.0002

Data Index: 589158 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.6092. Min Range: -0.6092

Max Act: 0.4312. Min Act: -0.0002

Data Index: 438044 (C4 (Web Text))

Max Activating Token Index: 971