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

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

Neuron 419 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: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1159440 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0644. Min Act: -0.0002

Data Index: 617133 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0497. Min Act: -0.0002

Data Index: 826471 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0499. Min Act: -0.0002

Data Index: 959269 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0474. Min Act: -0.0002

Data Index: 65281 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0452. Min Act: -0.0002

Data Index: 997504 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0479. Min Act: -0.0002

Data Index: 670384 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0446. Min Act: -0.0002

Data Index: 36215 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1290905 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0454. Min Act: -0.0002

Data Index: 564161 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0455. Min Act: -0.0002

Data Index: 395057 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0457. Min Act: -0.0002

Data Index: 624540 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1043026 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0421. Min Act: -0.0002

Data Index: 810229 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1161340 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0424. Min Act: -0.0002

Data Index: 827192 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0427. Min Act: -0.0002

Data Index: 708215 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0402. Min Act: -0.0002

Data Index: 801280 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0412. Min Act: -0.0002

Data Index: 23093 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0400. Min Act: -0.0002

Data Index: 286006 (C4 (Web Text))

Max Activating Token Index: 724