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

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

Neuron 65 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0460. Min Act: -0.0006

Data Index: 1029106 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1118834 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0465. Min Act: -0.0006

Data Index: 978571 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0487. Min Act: -0.0006

Data Index: 374430 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0482. Min Act: -0.0006

Data Index: 269849 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0006

Data Index: 200743 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0006

Data Index: 971704 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0460. Min Act: -0.0006

Data Index: 385204 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1345131 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0435. Min Act: -0.0006

Data Index: 533006 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0427. Min Act: -0.0006

Data Index: 336396 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1272417 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0430. Min Act: -0.0006

Data Index: 745143 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0408. Min Act: -0.0006

Data Index: 801845 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1331909 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1248646 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0442. Min Act: -0.0006

Data Index: 521321 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0408. Min Act: -0.0006

Data Index: 898396 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0413. Min Act: -0.0006

Data Index: 999921 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0455. Min Act: -0.0006

Data Index: 335008 (C4 (Web Text))

Max Activating Token Index: 580