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

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

Neuron 129 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: 0.1947. Min Range: -0.1947

Max Act: 0.1892. Min Act: -0.0006

Data Index: 653036 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1947. Min Act: -0.0006

Data Index: 321308 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1866. Min Act: -0.0006

Data Index: 312688 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1706. Min Act: -0.0006

Data Index: 261603 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1751. Min Act: -0.0006

Data Index: 572501 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1734. Min Act: -0.0006

Data Index: 915823 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1542. Min Act: -0.0006

Data Index: 613325 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1548. Min Act: -0.0006

Data Index: 1186227 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1482. Min Act: -0.0006

Data Index: 1207227 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1538. Min Act: -0.0006

Data Index: 964948 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1536. Min Act: -0.0006

Data Index: 995655 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1602. Min Act: -0.0006

Data Index: 83601 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1593. Min Act: -0.0006

Data Index: 694358 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1593. Min Act: -0.0006

Data Index: 247344 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1525. Min Act: -0.0006

Data Index: 159313 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1396. Min Act: -0.0006

Data Index: 878570 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1447. Min Act: -0.0006

Data Index: 510893 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1425. Min Act: -0.0006

Data Index: 265507 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1376. Min Act: -0.0006

Data Index: 371807 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1421. Min Act: -0.0006

Data Index: 1318609 (C4 (Web Text))

Max Activating Token Index: 442