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

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

Neuron 114 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: 3.9232. Min Range: -3.9232

Max Act: 3.9232. Min Act: -0.1700

Data Index: 1337623 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8805. Min Act: -0.1700

Data Index: 738179 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8503. Min Act: -0.1700

Data Index: 685720 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8469. Min Act: -0.1700

Data Index: 26491 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8364. Min Act: -0.1700

Data Index: 770129 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1292581 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8366. Min Act: -0.1700

Data Index: 1281978 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8113. Min Act: -0.1700

Data Index: 1081911 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1091640 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7770. Min Act: -0.1700

Data Index: 126636 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7929. Min Act: -0.1700

Data Index: 900450 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1201801 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7765. Min Act: -0.1700

Data Index: 1040666 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7787. Min Act: -0.1700

Data Index: 1396386 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7432. Min Act: -0.1700

Data Index: 834174 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7610. Min Act: -0.1700

Data Index: 615932 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7393. Min Act: -0.1700

Data Index: 106913 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7300. Min Act: -0.1700

Data Index: 234068 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7475. Min Act: -0.1700

Data Index: 890869 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 3.9232. Min Range: -3.9232

Max Act: 3.7348. Min Act: -0.1700

Data Index: 1188118 (C4 (Web Text))

Max Activating Token Index: 190