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

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

Neuron 749 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.8247. Min Act: -0.1700

Data Index: 658589 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7308. Min Act: -0.1700

Data Index: 328926 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7621. Min Act: -0.1700

Data Index: 962572 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7621. Min Act: -0.1700

Data Index: 1228352 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7465. Min Act: -0.1700

Data Index: 669648 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7152. Min Act: -0.1700

Data Index: 1309909 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6996. Min Act: -0.1700

Data Index: 342381 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6839. Min Act: -0.1700

Data Index: 943622 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6996. Min Act: -0.1700

Data Index: 685058 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.7152. Min Act: -0.1700

Data Index: 1126970 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 334001 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6370. Min Act: -0.1700

Data Index: 703390 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6683. Min Act: -0.1700

Data Index: 991969 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6683. Min Act: -0.1700

Data Index: 1061955 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 1061248 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 860750 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 33456 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6370. Min Act: -0.1700

Data Index: 817641 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6213. Min Act: -0.1700

Data Index: 836014 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 3.8247. Min Range: -3.8247

Max Act: 3.6370. Min Act: -0.1700

Data Index: 840512 (C4 (Web Text))

Max Activating Token Index: 729