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

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

Neuron 2025 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: 3.0358. Min Range: -3.0358

Max Act: 3.0358. Min Act: -0.1700

Data Index: 68094 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 3.0358. Min Range: -3.0358

Max Act: 3.0137. Min Act: -0.1700

Data Index: 757748 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.9483. Min Act: -0.1684

Data Index: 1341154 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.9205. Min Act: -0.1700

Data Index: 1512344 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.9226. Min Act: -0.1700

Data Index: 877061 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.9029. Min Act: -0.1700

Data Index: 45296 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8800. Min Act: -0.1695

Data Index: 691454 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8735. Min Act: -0.1700

Data Index: 905493 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8824. Min Act: -0.1700

Data Index: 155890 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8881. Min Act: -0.1700

Data Index: 1333592 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8912. Min Act: -0.1700

Data Index: 1471057 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8809. Min Act: -0.1696

Data Index: 1380804 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8653. Min Act: -0.1700

Data Index: 1368482 (Python Code)

Max Activating Token Index: 431

Text #13

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8765. Min Act: -0.1699

Data Index: 1372355 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8689. Min Act: -0.1700

Data Index: 1276155 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8777. Min Act: -0.1652

Data Index: 280571 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8669. Min Act: -0.1700

Data Index: 146259 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8476. Min Act: -0.1700

Data Index: 917243 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8499. Min Act: -0.1652

Data Index: 935289 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.0358. Min Range: -3.0358

Max Act: 2.8410. Min Act: -0.1700

Data Index: 770470 (C4 (Web Text))

Max Activating Token Index: 545