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

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

Neuron 1373 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: 2.8765. Min Range: -2.8765

Max Act: 2.8765. Min Act: -0.1700

Data Index: 1629718 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8487. Min Act: -0.1700

Data Index: 1266746 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8519. Min Act: -0.1700

Data Index: 1614994 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8636. Min Act: -0.1700

Data Index: 1631946 (Python Code)

Max Activating Token Index: 638

Text #4

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8597. Min Act: -0.1700

Data Index: 1582171 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8448. Min Act: -0.1700

Data Index: 1255641 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8299. Min Act: -0.1700

Data Index: 1547581 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8325. Min Act: -0.1700

Data Index: 1053271 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8456. Min Act: -0.1700

Data Index: 992278 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8166. Min Act: -0.1700

Data Index: 1617398 (Python Code)

Max Activating Token Index: 156

Text #10

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8327. Min Act: -0.1700

Data Index: 1585866 (Python Code)

Max Activating Token Index: 745

Text #11

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8215. Min Act: -0.1700

Data Index: 1501488 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8390. Min Act: -0.1700

Data Index: 1557030 (Python Code)

Max Activating Token Index: 421

Text #13

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8334. Min Act: -0.1700

Data Index: 985313 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.7975. Min Act: -0.1700

Data Index: 1123125 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8134. Min Act: -0.1700

Data Index: 1398501 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.7993. Min Act: -0.1700

Data Index: 1380650 (Python Code)

Max Activating Token Index: 750

Text #17

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.8039. Min Act: -0.1700

Data Index: 1369999 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.7920. Min Act: -0.1700

Data Index: 1611046 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 2.8765. Min Range: -2.8765

Max Act: 2.7957. Min Act: -0.1700

Data Index: 945423 (C4 (Web Text))

Max Activating Token Index: 866