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

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

Neuron 101 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0705. Min Range: -5.0705

Max Act: 5.0393. Min Act: -0.1700

Data Index: 785985 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 5.0705. Min Range: -5.0705

Max Act: 5.0705. Min Act: -0.1700

Data Index: 1193 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.9768. Min Act: -0.1700

Data Index: 276703 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.9455. Min Act: -0.1700

Data Index: 637597 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.9143. Min Act: -0.1700

Data Index: 385883 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.9768. Min Act: -0.1700

Data Index: 804504 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.9768. Min Act: -0.1700

Data Index: 1216304 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 936235 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 1207084 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 168717 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8830. Min Act: -0.1700

Data Index: 104148 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.9143. Min Act: -0.1700

Data Index: 1293409 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8205. Min Act: -0.1700

Data Index: 669278 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8205. Min Act: -0.1700

Data Index: 105713 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 650795 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 1078236 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8205. Min Act: -0.1700

Data Index: 867117 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 860574 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8518. Min Act: -0.1700

Data Index: 589472 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 5.0705. Min Range: -5.0705

Max Act: 4.8205. Min Act: -0.1700

Data Index: 968820 (C4 (Web Text))

Max Activating Token Index: 568