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

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

Neuron 1374 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: 3.7265. Min Range: -3.7265

Max Act: 3.7265. Min Act: -0.1700

Data Index: 1278553 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.6853. Min Act: -0.1700

Data Index: 1332123 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.6354. Min Act: -0.1700

Data Index: 49618 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.6150. Min Act: -0.1700

Data Index: 333059 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5966. Min Act: -0.1700

Data Index: 242848 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5584. Min Act: -0.1700

Data Index: 818723 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.6056. Min Act: -0.1700

Data Index: 1252665 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5762. Min Act: -0.1700

Data Index: 689829 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5400. Min Act: -0.1700

Data Index: 977508 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5661. Min Act: -0.1700

Data Index: 487828 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5186. Min Act: -0.1700

Data Index: 139896 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5398. Min Act: -0.1700

Data Index: 942546 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5433. Min Act: -0.1700

Data Index: 977519 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5408. Min Act: -0.1700

Data Index: 400086 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5287. Min Act: -0.1700

Data Index: 737407 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5493. Min Act: -0.1700

Data Index: 901587 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5214. Min Act: -0.1700

Data Index: 1184929 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1208500 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.4968. Min Act: -0.1700

Data Index: 815759 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 3.7265. Min Range: -3.7265

Max Act: 3.4932. Min Act: -0.1700

Data Index: 236270 (C4 (Web Text))

Max Activating Token Index: 708