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

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

Neuron 928 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: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0004

Data Index: 779862 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0470. Min Act: -0.0003

Data Index: 189997 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0468. Min Act: -0.0003

Data Index: 396766 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0466. Min Act: -0.0003

Data Index: 969669 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0446. Min Act: -0.0003

Data Index: 964570 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0445. Min Act: -0.0003

Data Index: 756949 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0461. Min Act: -0.0002

Data Index: 391527 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1166488 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0443. Min Act: -0.0003

Data Index: 600832 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0448. Min Act: -0.0003

Data Index: 581718 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0454. Min Act: -0.0002

Data Index: 554010 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0441. Min Act: -0.0003

Data Index: 4288 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0438. Min Act: -0.0003

Data Index: 128159 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0442. Min Act: -0.0003

Data Index: 72013 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0424. Min Act: -0.0003

Data Index: 129715 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0425. Min Act: -0.0004

Data Index: 1237715 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0416. Min Act: -0.0003

Data Index: 251772 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0423. Min Act: -0.0003

Data Index: 432287 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0421. Min Act: -0.0003

Data Index: 120441 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0415. Min Act: -0.0003

Data Index: 138951 (C4 (Web Text))

Max Activating Token Index: 813