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

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

Neuron 1820 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: 5.6861. Min Range: -5.6861

Max Act: 5.6861. Min Act: -0.1700

Data Index: 312722 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.5611. Min Act: -0.1700

Data Index: 569962 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.5611. Min Act: -0.1700

Data Index: 227985 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4986. Min Act: -0.1700

Data Index: 487026 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.5299. Min Act: -0.1700

Data Index: 1173248 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4986. Min Act: -0.1700

Data Index: 967508 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.5611. Min Act: -0.1700

Data Index: 673866 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4361. Min Act: -0.1700

Data Index: 1190712 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4986. Min Act: -0.1700

Data Index: 814583 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4674. Min Act: -0.1700

Data Index: 212552 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4361. Min Act: -0.1700

Data Index: 611715 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4361. Min Act: -0.1700

Data Index: 105200 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.3736. Min Act: -0.1700

Data Index: 492711 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4986. Min Act: -0.1700

Data Index: 333718 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4049. Min Act: -0.1700

Data Index: 1300270 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4049. Min Act: -0.1700

Data Index: 1335975 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4049. Min Act: -0.1700

Data Index: 1245661 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.3736. Min Act: -0.1700

Data Index: 323284 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4361. Min Act: -0.1700

Data Index: 1347099 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 5.6861. Min Range: -5.6861

Max Act: 5.4049. Min Act: -0.1700

Data Index: 155798 (C4 (Web Text))

Max Activating Token Index: 544