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

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

Neuron 1019 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: 3.2075. Min Range: -3.2075

Max Act: 3.2075. Min Act: -0.1418

Data Index: 1656354 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.1753. Min Act: -0.1700

Data Index: 1448452 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.1239. Min Act: -0.1699

Data Index: 1602140 (Python Code)

Max Activating Token Index: 743

Text #3

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.0803. Min Act: -0.1696

Data Index: 1590387 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.0821. Min Act: -0.0321

Data Index: 1496222 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.0369. Min Act: -0.1699

Data Index: 1473458 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.0112. Min Act: -0.1699

Data Index: 425498 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 3.2075. Min Range: -3.2075

Max Act: 3.0268. Min Act: -0.1700

Data Index: 1545348 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9955. Min Act: -0.1700

Data Index: 698790 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9815. Min Act: -0.1700

Data Index: 1382924 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9888. Min Act: -0.0321

Data Index: 1565195 (Python Code)

Max Activating Token Index: 429

Text #11

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9523. Min Act: -0.1700

Data Index: 1487942 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9817. Min Act: -0.1700

Data Index: 1401892 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9463. Min Act: -0.0321

Data Index: 1531992 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9485. Min Act: -0.1700

Data Index: 865923 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9204. Min Act: -0.1699

Data Index: 1365816 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9341. Min Act: -0.0865

Data Index: 1639744 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9156. Min Act: -0.1697

Data Index: 526029 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9244. Min Act: -0.1700

Data Index: 717515 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.2075. Min Range: -3.2075

Max Act: 2.9033. Min Act: -0.1700

Data Index: 1650424 (Python Code)

Max Activating Token Index: 898