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

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

Neuron 4756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3820. Min Range: -4.3820

Max Act: 4.3820. Min Act: -0.0000

Data Index: 932740 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 4.3820. Min Range: -4.3820

Max Act: 4.2327. Min Act: -0.0000

Data Index: 676864 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 4.3820. Min Range: -4.3820

Max Act: 4.1781. Min Act: -0.0000

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.9369. Min Act: -0.0000

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 4.3820. Min Range: -4.3820

Max Act: 4.0320. Min Act: -0.0000

Data Index: 1015978 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.7613. Min Act: -0.0000

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.8230. Min Act: -0.0000

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.7087. Min Act: -0.0000

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.4898. Min Act: -0.0000

Data Index: 248455 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.4740. Min Act: -0.0000

Data Index: 67857 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.7941. Min Act: -0.0000

Data Index: 1245651 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.5682. Min Act: -0.0000

Data Index: 608364 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.4029. Min Act: -0.0000

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.3557. Min Act: -0.0000

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.2941. Min Act: -0.0000

Data Index: 1259665 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.3746. Min Act: -0.0000

Data Index: 551587 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.3527. Min Act: -0.0000

Data Index: 1007079 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.0698. Min Act: -0.0000

Data Index: 987492 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.3521. Min Act: -0.0000

Data Index: 990307 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 4.3820. Min Range: -4.3820

Max Act: 3.3352. Min Act: -0.0000

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 971