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

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

Neuron 776 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.7910. Min Act: -0.1700

Data Index: 1231103 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.7598. Min Act: -0.1700

Data Index: 1356072 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.7910. Min Act: -0.1700

Data Index: 534952 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.7285. Min Act: -0.1700

Data Index: 1355850 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6660. Min Act: -0.1700

Data Index: 65494 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6660. Min Act: -0.1700

Data Index: 186484 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6660. Min Act: -0.1699

Data Index: 54712 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6973. Min Act: -0.1700

Data Index: 809967 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6348. Min Act: -0.1700

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.5723. Min Act: -0.1700

Data Index: 843654 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6660. Min Act: -0.1700

Data Index: 1325751 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6035. Min Act: -0.1700

Data Index: 883095 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.6348. Min Act: -0.1700

Data Index: 60011 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.5723. Min Act: -0.1700

Data Index: 1131533 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.5723. Min Act: -0.1700

Data Index: 431175 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.5410. Min Act: -0.1700

Data Index: 1017698 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.5410. Min Act: -0.1700

Data Index: 1118073 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.4785. Min Act: -0.1700

Data Index: 531852 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.5723. Min Act: -0.1700

Data Index: 191808 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 5.7910. Min Range: -5.7910

Max Act: 5.4785. Min Act: -0.1700

Data Index: 896220 (C4 (Web Text))

Max Activating Token Index: 456