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

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

Neuron 105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0002

Data Index: 961856 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0477. Min Act: -0.0002

Data Index: 636699 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0470. Min Act: -0.0002

Data Index: 274383 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1105428 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1219945 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1025613 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0401. Min Act: -0.0002

Data Index: 785725 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1143996 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0414. Min Act: -0.0002

Data Index: 790265 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0426. Min Act: -0.0002

Data Index: 83963 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0417. Min Act: -0.0002

Data Index: 782771 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1051221 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0384. Min Act: -0.0002

Data Index: 717143 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0390. Min Act: -0.0002

Data Index: 949461 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0388. Min Act: -0.0002

Data Index: 386913 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1039029 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0364. Min Act: -0.0002

Data Index: 307428 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1250384 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1038050 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0364. Min Act: -0.0002

Data Index: 375381 (C4 (Web Text))

Max Activating Token Index: 270