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

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

Neuron 283 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: 3.9385. Min Range: -3.9385

Max Act: 3.9385. Min Act: -0.1700

Data Index: 499015 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1526459 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.5328. Min Act: -0.1700

Data Index: 1469721 (Python Code)

Max Activating Token Index: 828

Text #3

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.5140. Min Act: -0.1700

Data Index: 1425336 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4905. Min Act: -0.1700

Data Index: 1602405 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.5629. Min Act: -0.1700

Data Index: 1440735 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.5246. Min Act: -0.1700

Data Index: 1506477 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4597. Min Act: -0.1700

Data Index: 1636849 (Python Code)

Max Activating Token Index: 872

Text #8

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.5227. Min Act: -0.1700

Data Index: 1467165 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4652. Min Act: -0.1700

Data Index: 1589083 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4794. Min Act: -0.1700

Data Index: 1370728 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4628. Min Act: -0.1700

Data Index: 1409379 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4819. Min Act: -0.1700

Data Index: 1643312 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4841. Min Act: -0.1700

Data Index: 1485466 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4808. Min Act: -0.1700

Data Index: 1586260 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4472. Min Act: -0.1700

Data Index: 1367074 (Python Code)

Max Activating Token Index: 714

Text #16

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4378. Min Act: -0.1700

Data Index: 1537761 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4366. Min Act: -0.1700

Data Index: 1443455 (Python Code)

Max Activating Token Index: 681

Text #18

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4126. Min Act: -0.1700

Data Index: 1369986 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 3.9385. Min Range: -3.9385

Max Act: 3.4388. Min Act: -0.1700

Data Index: 1565398 (Python Code)

Max Activating Token Index: 707