Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3659 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1181305 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5139. Min Act: -0.0000

Data Index: 597972 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1062163 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4889. Min Act: -0.0000

Data Index: 860110 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1276114 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1332140 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4450. Min Act: 0.0002

Data Index: 1633149 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1182301 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4466. Min Act: -0.0000

Data Index: 933307 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4133. Min Act: -0.0000

Data Index: 1415716 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3899. Min Act: -0.0000

Data Index: 695020 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4106. Min Act: -0.0000

Data Index: 965043 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4074. Min Act: -0.0000

Data Index: 491195 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4166. Min Act: 0.0002

Data Index: 1599908 (Python Code)

Max Activating Token Index: 723

Text #14

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4186. Min Act: -0.0000

Data Index: 614707 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3882. Min Act: -0.0000

Data Index: 662594 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4423. Min Act: -0.0000

Data Index: 50105 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1024383 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3816. Min Act: -0.0000

Data Index: 684781 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3856. Min Act: -0.0000

Data Index: 386395 (C4 (Web Text))

Max Activating Token Index: 432