Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5641 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.7125. Min Act: -0.0000

Data Index: 1586922 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.2651. Min Act: -0.0000

Data Index: 1569176 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.5951. Min Act: -0.0000

Data Index: 1566176 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.7237. Min Act: -0.0000

Data Index: 1534749 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.7076. Min Act: -0.0000

Data Index: 1542427 (Python Code)

Max Activating Token Index: 482

Text #5

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.8153. Min Act: -0.0000

Data Index: 1555165 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.6807. Min Act: -0.0000

Data Index: 1634238 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.6781. Min Act: -0.0000

Data Index: 1645278 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.5643. Min Act: -0.0000

Data Index: 1600980 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.5180. Min Act: -0.0000

Data Index: 1382190 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.6097. Min Act: -0.0000

Data Index: 1604382 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.5772. Min Act: -0.0000

Data Index: 1462219 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.4476. Min Act: -0.0000

Data Index: 1387933 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.4736. Min Act: -0.0000

Data Index: 1494579 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.3583. Min Act: -0.0000

Data Index: 1629299 (Python Code)

Max Activating Token Index: 327

Text #15

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.3181. Min Act: -0.0000

Data Index: 1555252 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.5609. Min Act: -0.0000

Data Index: 1363794 (Python Code)

Max Activating Token Index: 532

Text #17

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.4425. Min Act: -0.0000

Data Index: 1496373 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.4971. Min Act: -0.0000

Data Index: 1492778 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 3.7125. Min Range: -3.7125

Max Act: 2.2580. Min Act: -0.0000

Data Index: 1458802 (Python Code)

Max Activating Token Index: 212