Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1932 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0003

Data Index: 584177 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0436. Min Act: -0.0003

Data Index: 876332 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0437. Min Act: -0.0002

Data Index: 678845 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0414. Min Act: -0.0001

Data Index: 368137 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1071804 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0400. Min Act: -0.0002

Data Index: 590390 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0401. Min Act: -0.0003

Data Index: 64539 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0408. Min Act: -0.0002

Data Index: 176571 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0402. Min Act: -0.0003

Data Index: 773666 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1128216 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0405. Min Act: -0.0002

Data Index: 374485 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0404. Min Act: -0.0003

Data Index: 71502 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0385. Min Act: -0.0002

Data Index: 287898 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0394. Min Act: -0.0003

Data Index: 125055 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1187416 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0391. Min Act: -0.0002

Data Index: 675719 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1264473 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0381. Min Act: -0.0002

Data Index: 910709 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0396. Min Act: -0.0003

Data Index: 433286 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0384. Min Act: -0.0002

Data Index: 774090 (C4 (Web Text))

Max Activating Token Index: 425