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

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

Neuron 555 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: 1.0969. Min Range: -1.0969

Max Act: 1.0969. Min Act: -0.0002

Data Index: 94554 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.9792. Min Act: -0.0001

Data Index: 677477 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8811. Min Act: -0.0001

Data Index: 38118 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.9405. Min Act: -0.0002

Data Index: 954720 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8580. Min Act: -0.0001

Data Index: 374347 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8072. Min Act: -0.0001

Data Index: 145059 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8828. Min Act: -0.0001

Data Index: 275755 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7095. Min Act: -0.0001

Data Index: 317436 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8384. Min Act: -0.0001

Data Index: 1311002 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8787. Min Act: -0.0002

Data Index: 22365 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7976. Min Act: -0.0001

Data Index: 660456 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8048. Min Act: -0.0001

Data Index: 1053306 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7343. Min Act: -0.0002

Data Index: 694982 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7476. Min Act: -0.0001

Data Index: 92288 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.6816. Min Act: -0.0001

Data Index: 963867 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8107. Min Act: -0.0002

Data Index: 1014949 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7695. Min Act: -0.0002

Data Index: 222955 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7606. Min Act: -0.0001

Data Index: 193588 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.7859. Min Act: -0.0001

Data Index: 739144 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.0969. Min Range: -1.0969

Max Act: 0.8177. Min Act: -0.0001

Data Index: 383445 (C4 (Web Text))

Max Activating Token Index: 700