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

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

Neuron 1628 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: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0003

Data Index: 11264 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1097459 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0509. Min Act: -0.0003

Data Index: 272791 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0535. Min Act: -0.0003

Data Index: 357144 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0509. Min Act: -0.0002

Data Index: 654174 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0468. Min Act: -0.0003

Data Index: 187759 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0483. Min Act: -0.0002

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0458. Min Act: -0.0003

Data Index: 504912 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1171632 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0448. Min Act: -0.0003

Data Index: 701206 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0462. Min Act: -0.0003

Data Index: 495425 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1351565 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0474. Min Act: -0.0003

Data Index: 615974 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1195756 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0443. Min Act: -0.0003

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0461. Min Act: -0.0002

Data Index: 269743 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0442. Min Act: -0.0003

Data Index: 799647 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0437. Min Act: -0.0003

Data Index: 287974 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0433. Min Act: -0.0003

Data Index: 596184 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0423. Min Act: -0.0003

Data Index: 777322 (C4 (Web Text))

Max Activating Token Index: 919