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

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

Neuron 1606 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: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0006

Data Index: 639724 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0455. Min Act: -0.0006

Data Index: 372012 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0450. Min Act: -0.0006

Data Index: 740029 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0432. Min Act: -0.0006

Data Index: 973678 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0407. Min Act: -0.0006

Data Index: 1341874 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0440. Min Act: -0.0006

Data Index: 477685 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1346270 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0434. Min Act: -0.0006

Data Index: 23717 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0402. Min Act: -0.0006

Data Index: 639532 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0433. Min Act: -0.0006

Data Index: 1096686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0338. Min Act: -0.0006

Data Index: 394761 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0339. Min Act: -0.0006

Data Index: 972765 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0398. Min Act: -0.0006

Data Index: 96481 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1102217 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0369. Min Act: -0.0006

Data Index: 322699 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0384. Min Act: -0.0006

Data Index: 667012 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0385. Min Act: -0.0006

Data Index: 848660 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0384. Min Act: -0.0006

Data Index: 85799 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0392. Min Act: -0.0006

Data Index: 503024 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0398. Min Act: -0.0006

Data Index: 371995 (C4 (Web Text))

Max Activating Token Index: 570