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

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

Neuron 2011 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0104. Min Range: -4.0104

Max Act: 4.0104. Min Act: -0.1700

Data Index: 292520 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.7915. Min Act: -0.1700

Data Index: 938275 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.7915. Min Act: -0.1700

Data Index: 223675 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.6664. Min Act: -0.1700

Data Index: 320326 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.6664. Min Act: -0.1700

Data Index: 172680 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.6664. Min Act: -0.1700

Data Index: 207943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.6977. Min Act: -0.1700

Data Index: 901642 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.6037. Min Act: -0.1700

Data Index: 1318419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5724. Min Act: -0.1700

Data Index: 867348 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.6037. Min Act: -0.1700

Data Index: 101906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5411. Min Act: -0.1700

Data Index: 1226604 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5411. Min Act: -0.1700

Data Index: 626092 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5724. Min Act: -0.1700

Data Index: 127895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5724. Min Act: -0.1700

Data Index: 770701 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5411. Min Act: -0.1700

Data Index: 932482 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5411. Min Act: -0.1700

Data Index: 404229 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5411. Min Act: -0.1700

Data Index: 764086 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1118194 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5411. Min Act: -0.1700

Data Index: 94486 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 4.0104. Min Range: -4.0104

Max Act: 3.5098. Min Act: -0.1700

Data Index: 910300 (C4 (Web Text))

Max Activating Token Index: 880