Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7072. Min Range: -3.7072

Max Act: 3.5666. Min Act: -0.0000

Data Index: 1311765 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 3.7072. Min Range: -3.7072

Max Act: 3.7072. Min Act: -0.0000

Data Index: 866077 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 3.7072. Min Range: -3.7072

Max Act: 3.3952. Min Act: -0.0000

Data Index: 1314771 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 3.7072. Min Range: -3.7072

Max Act: 3.1907. Min Act: -0.0000

Data Index: 1195220 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.7328. Min Act: -0.0000

Data Index: 1346746 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.5710. Min Act: -0.0000

Data Index: 1160898 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.5185. Min Act: -0.0000

Data Index: 644514 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.5434. Min Act: -0.0000

Data Index: 1223308 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.0421. Min Act: -0.0000

Data Index: 1171573 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.3331. Min Act: -0.0000

Data Index: 356432 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.4946. Min Act: -0.0000

Data Index: 1095756 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.1268. Min Act: -0.0000

Data Index: 421261 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.4659. Min Act: -0.0000

Data Index: 200155 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.3247. Min Act: -0.0000

Data Index: 584408 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.4064. Min Act: -0.0000

Data Index: 540409 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.1644. Min Act: -0.0000

Data Index: 506496 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.3572. Min Act: -0.0000

Data Index: 1077927 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.3563. Min Act: -0.0000

Data Index: 864936 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.1091. Min Act: -0.0000

Data Index: 890075 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 3.7072. Min Range: -3.7072

Max Act: 2.1172. Min Act: -0.0000

Data Index: 119711 (C4 (Web Text))

Max Activating Token Index: 760