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

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

Neuron 944 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: 3.7125. Min Range: -3.7125

Max Act: 3.7125. Min Act: -0.1700

Data Index: 898034 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1073564 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4616. Min Act: -0.1700

Data Index: 527588 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4550. Min Act: -0.1700

Data Index: 565876 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4336. Min Act: -0.1700

Data Index: 69828 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4334. Min Act: -0.1700

Data Index: 150063 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4304. Min Act: -0.1700

Data Index: 1080137 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4359. Min Act: -0.1700

Data Index: 585326 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.4071. Min Act: -0.1700

Data Index: 1112707 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3820. Min Act: -0.1700

Data Index: 566979 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3896. Min Act: -0.1700

Data Index: 470652 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3712. Min Act: -0.1700

Data Index: 944275 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3799. Min Act: -0.1700

Data Index: 1099211 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3760. Min Act: -0.1700

Data Index: 1114936 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3868. Min Act: -0.1699

Data Index: 514756 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3710. Min Act: -0.1700

Data Index: 332623 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3540. Min Act: -0.1700

Data Index: 160998 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3562. Min Act: -0.1700

Data Index: 339192 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3517. Min Act: -0.1700

Data Index: 833833 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.7125. Min Range: -3.7125

Max Act: 3.3377. Min Act: -0.1700

Data Index: 397024 (C4 (Web Text))

Max Activating Token Index: 963