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

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

Neuron 1759 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: 4.1254. Min Range: -4.1254

Max Act: 4.1254. Min Act: -0.1700

Data Index: 1537893 (Python Code)

Max Activating Token Index: 321

Text #1

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.9747. Min Act: -0.1700

Data Index: 1371093 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.9709. Min Act: -0.1700

Data Index: 1636580 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.9351. Min Act: -0.1700

Data Index: 1558924 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8884. Min Act: -0.1700

Data Index: 1616987 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8611. Min Act: -0.1700

Data Index: 1365592 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8638. Min Act: -0.1700

Data Index: 1540699 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8320. Min Act: -0.1700

Data Index: 1651198 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8503. Min Act: -0.1700

Data Index: 1582774 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8457. Min Act: -0.1700

Data Index: 1615630 (Python Code)

Max Activating Token Index: 194

Text #10

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8146. Min Act: -0.1700

Data Index: 1385404 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8146. Min Act: -0.1700

Data Index: 1605264 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8258. Min Act: -0.1700

Data Index: 1517635 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.8158. Min Act: -0.1700

Data Index: 1513609 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.7686. Min Act: -0.1700

Data Index: 1511292 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.7620. Min Act: -0.1700

Data Index: 1460827 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.7733. Min Act: -0.1700

Data Index: 1605557 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.7071. Min Act: -0.1700

Data Index: 1650952 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.7473. Min Act: -0.1700

Data Index: 1563928 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 4.1254. Min Range: -4.1254

Max Act: 3.7370. Min Act: -0.1700

Data Index: 1464319 (Python Code)

Max Activating Token Index: 707