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

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

Neuron 4440 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: 2.1069. Min Range: -2.1069

Max Act: 2.1069. Min Act: -0.0000

Data Index: 429793 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.9980. Min Act: -0.0000

Data Index: 677145 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.9182. Min Act: -0.0000

Data Index: 551688 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.5322. Min Act: -0.0000

Data Index: 166606 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.6052. Min Act: -0.0000

Data Index: 959592 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.3709. Min Act: -0.0000

Data Index: 1093207 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1038678 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1265236 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.3130. Min Act: -0.0000

Data Index: 66824 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1272654 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2096. Min Act: -0.0000

Data Index: 484543 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.4060. Min Act: -0.0000

Data Index: 685337 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2609. Min Act: -0.0000

Data Index: 847946 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.3192. Min Act: -0.0000

Data Index: 791428 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1041740 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2406. Min Act: -0.0000

Data Index: 113246 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2159. Min Act: -0.0000

Data Index: 840855 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2189. Min Act: -0.0000

Data Index: 796266 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2259. Min Act: -0.0000

Data Index: 194745 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2675. Min Act: -0.0000

Data Index: 779083 (C4 (Web Text))

Max Activating Token Index: 112