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

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

Neuron 5036 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.6166. Min Act: -0.0002

Data Index: 1429361 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.5269. Min Act: -0.0002

Data Index: 1537238 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.4615. Min Act: -0.0002

Data Index: 1472415 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.4702. Min Act: -0.0002

Data Index: 1397207 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.4389. Min Act: -0.0002

Data Index: 1470659 (Python Code)

Max Activating Token Index: 233

Text #5

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3764. Min Act: -0.0002

Data Index: 1425872 (Python Code)

Max Activating Token Index: 444

Text #6

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3796. Min Act: -0.0002

Data Index: 1419034 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3601. Min Act: -0.0002

Data Index: 1398093 (Python Code)

Max Activating Token Index: 197

Text #8

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3895. Min Act: -0.0002

Data Index: 1395709 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3583. Min Act: -0.0002

Data Index: 1368341 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3471. Min Act: -0.0002

Data Index: 1429436 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3122. Min Act: -0.0002

Data Index: 1454045 (Python Code)

Max Activating Token Index: 459

Text #12

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.3153. Min Act: -0.0002

Data Index: 1375950 (Python Code)

Max Activating Token Index: 837

Text #13

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2720. Min Act: -0.0002

Data Index: 1411532 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2934. Min Act: -0.0002

Data Index: 1412549 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2740. Min Act: -0.0002

Data Index: 1447798 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2693. Min Act: -0.0002

Data Index: 1425540 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2737. Min Act: -0.0002

Data Index: 1495591 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2615. Min Act: -0.0002

Data Index: 1381489 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 1.6166. Min Range: -1.6166

Max Act: 1.2527. Min Act: -0.0002

Data Index: 1408303 (Python Code)

Max Activating Token Index: 942