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

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

Neuron 1896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0005

Data Index: 1082946 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0456. Min Act: -0.0005

Data Index: 1643271 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0478. Min Act: -0.0005

Data Index: 699869 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0481. Min Act: -0.0005

Data Index: 1603938 (Python Code)

Max Activating Token Index: 427

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1395461 (Python Code)

Max Activating Token Index: 783

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0465. Min Act: -0.0005

Data Index: 1495778 (Python Code)

Max Activating Token Index: 647

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0456. Min Act: -0.0005

Data Index: 1475198 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0443. Min Act: -0.0005

Data Index: 842590 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0458. Min Act: -0.0005

Data Index: 164488 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0460. Min Act: -0.0005

Data Index: 1472054 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0463. Min Act: -0.0005

Data Index: 1573843 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0446. Min Act: -0.0005

Data Index: 1483804 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1266964 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1148526 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0449. Min Act: -0.0005

Data Index: 1368288 (Python Code)

Max Activating Token Index: 769

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0469. Min Act: -0.0005

Data Index: 1548139 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0447. Min Act: -0.0005

Data Index: 604494 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1630414 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0454. Min Act: -0.0005

Data Index: 1391670 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0438. Min Act: -0.0005

Data Index: 1454426 (Python Code)

Max Activating Token Index: 297