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

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

Neuron 1734 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3574. Min Act: -0.0005

Data Index: 875913 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2877. Min Act: -0.0005

Data Index: 1278022 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3024. Min Act: -0.0005

Data Index: 135075 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2994. Min Act: -0.0005

Data Index: 364114 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3084. Min Act: -0.0005

Data Index: 1133678 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2942. Min Act: -0.0005

Data Index: 1152485 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2940. Min Act: -0.0005

Data Index: 716384 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3176. Min Act: -0.0005

Data Index: 321921 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2953. Min Act: -0.0005

Data Index: 1533258 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3046. Min Act: -0.0005

Data Index: 832069 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2730. Min Act: -0.0005

Data Index: 1291210 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3030. Min Act: -0.0005

Data Index: 972832 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2886. Min Act: -0.0005

Data Index: 443654 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2928. Min Act: -0.0005

Data Index: 744639 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3338. Min Act: -0.0005

Data Index: 127652 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2869. Min Act: -0.0005

Data Index: 91917 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2878. Min Act: -0.0005

Data Index: 793370 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2779. Min Act: -0.0005

Data Index: 14095 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2762. Min Act: -0.0005

Data Index: 617235 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3050. Min Act: -0.0005

Data Index: 426797 (C4 (Web Text))

Max Activating Token Index: 177