Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1310 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.7808. Min Act: -0.1700

Data Index: 737554 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.7183. Min Act: -0.1700

Data Index: 261024 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.6557. Min Act: -0.1700

Data Index: 1163600 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.6870. Min Act: -0.1700

Data Index: 395931 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.6557. Min Act: -0.1700

Data Index: 891533 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.6557. Min Act: -0.1700

Data Index: 790227 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.5930. Min Act: -0.1700

Data Index: 57056 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.6557. Min Act: -0.1700

Data Index: 724792 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.5617. Min Act: -0.1700

Data Index: 1262006 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.5617. Min Act: -0.1700

Data Index: 710228 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.5617. Min Act: -0.1700

Data Index: 659805 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4991. Min Act: -0.1700

Data Index: 288203 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4364. Min Act: -0.1700

Data Index: 121158 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4677. Min Act: -0.1700

Data Index: 284810 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4677. Min Act: -0.1700

Data Index: 547580 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4677. Min Act: -0.1700

Data Index: 831739 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4364. Min Act: -0.1700

Data Index: 364171 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4364. Min Act: -0.1700

Data Index: 843921 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4364. Min Act: -0.1700

Data Index: 770796 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 3.7808. Min Range: -3.7808

Max Act: 3.4677. Min Act: -0.1700

Data Index: 347666 (C4 (Web Text))

Max Activating Token Index: 443