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

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

Neuron 1614 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: 3.5645. Min Range: -3.5645

Max Act: 3.5645. Min Act: -0.1700

Data Index: 1336195 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.5331. Min Act: -0.1700

Data Index: 478018 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.5331. Min Act: -0.1700

Data Index: 778569 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.5018. Min Act: -0.1700

Data Index: 633146 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4861. Min Act: -0.1700

Data Index: 206402 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4705. Min Act: -0.1700

Data Index: 94286 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4705. Min Act: -0.1700

Data Index: 1192476 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4861. Min Act: -0.1700

Data Index: 1215886 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4705. Min Act: -0.1700

Data Index: 1004133 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4391. Min Act: -0.1700

Data Index: 1200745 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4548. Min Act: -0.1700

Data Index: 209752 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4548. Min Act: -0.1700

Data Index: 352081 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4705. Min Act: -0.1700

Data Index: 746806 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4705. Min Act: -0.1700

Data Index: 712388 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4234. Min Act: -0.1700

Data Index: 1232451 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4391. Min Act: -0.1700

Data Index: 514000 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4234. Min Act: -0.1700

Data Index: 503396 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4077. Min Act: -0.1700

Data Index: 722373 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4234. Min Act: -0.1700

Data Index: 231758 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.5645. Min Range: -3.5645

Max Act: 3.4077. Min Act: -0.1700

Data Index: 730777 (C4 (Web Text))

Max Activating Token Index: 988