Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 501 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.5408. Min Act: -0.1700

Data Index: 19496 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.4625. Min Act: -0.1700

Data Index: 767501 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.3998. Min Act: -0.1700

Data Index: 907934 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.3370. Min Act: -0.1700

Data Index: 926457 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.2270. Min Act: -0.1700

Data Index: 944406 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.2270. Min Act: -0.1700

Data Index: 1014563 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.2113. Min Act: -0.1700

Data Index: 986103 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1321789 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1798. Min Act: -0.1700

Data Index: 303852 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1798. Min Act: -0.1700

Data Index: 895137 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1798. Min Act: -0.1700

Data Index: 1340280 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1798. Min Act: -0.1700

Data Index: 497037 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1168. Min Act: -0.1700

Data Index: 29662 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1484. Min Act: -0.1700

Data Index: 1248164 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1168. Min Act: -0.1700

Data Index: 168180 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.0695. Min Act: -0.1700

Data Index: 742398 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.0695. Min Act: -0.1700

Data Index: 1220313 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.0538. Min Act: -0.1700

Data Index: 258402 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.0538. Min Act: -0.1700

Data Index: 1272886 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.0538. Min Act: -0.1700

Data Index: 768956 (C4 (Web Text))

Max Activating Token Index: 834