Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1567 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.3020. Min Act: -0.1080

Data Index: 1481516 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0520. Min Act: -0.1693

Data Index: 1485761 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0461. Min Act: -0.1699

Data Index: 1491757 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0049. Min Act: -0.1699

Data Index: 1428890 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0012. Min Act: -0.0680

Data Index: 1362544 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9771. Min Act: -0.1563

Data Index: 1650294 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9746. Min Act: -0.1700

Data Index: 1516997 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9739. Min Act: -0.1699

Data Index: 1485886 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9576. Min Act: -0.1700

Data Index: 1521125 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9586. Min Act: -0.1699

Data Index: 1491518 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9510. Min Act: -0.1700

Data Index: 1545554 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9489. Min Act: -0.1700

Data Index: 1433097 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9706. Min Act: -0.1695

Data Index: 1468956 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9497. Min Act: -0.1305

Data Index: 1365718 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9483. Min Act: -0.1700

Data Index: 1466595 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9294. Min Act: -0.1667

Data Index: 1424823 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9066. Min Act: -0.1683

Data Index: 1423759 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9103. Min Act: -0.1700

Data Index: 1526262 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9175. Min Act: -0.1686

Data Index: 1428739 (Python Code)

Max Activating Token Index: 498

Text #19

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9170. Min Act: -0.1687

Data Index: 1616906 (Python Code)

Max Activating Token Index: 705