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

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

Neuron 561 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: 0.0517. Min Range: -0.0517

Max Act: 0.0504. Min Act: -0.0005

Data Index: 899609 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0005

Data Index: 617594 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0506. Min Act: -0.0005

Data Index: 984283 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0474. Min Act: -0.0005

Data Index: 814188 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0470. Min Act: -0.0005

Data Index: 870312 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0472. Min Act: -0.0005

Data Index: 531918 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0458. Min Act: -0.0005

Data Index: 488068 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0464. Min Act: -0.0005

Data Index: 1280177 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0457. Min Act: -0.0005

Data Index: 669629 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0475. Min Act: -0.0005

Data Index: 577228 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0455. Min Act: -0.0005

Data Index: 1257393 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0453. Min Act: -0.0005

Data Index: 787155 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0451. Min Act: -0.0005

Data Index: 1001077 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0438. Min Act: -0.0005

Data Index: 222175 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0446. Min Act: -0.0005

Data Index: 727799 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1248101 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0442. Min Act: -0.0005

Data Index: 1003153 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0441. Min Act: -0.0005

Data Index: 705453 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0440. Min Act: -0.0005

Data Index: 482906 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0436. Min Act: -0.0005

Data Index: 857867 (C4 (Web Text))

Max Activating Token Index: 32