Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 293 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.5531. Min Act: -0.1699

Data Index: 259547 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1325103 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.4983. Min Act: -0.1700

Data Index: 1402853 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.4677. Min Act: -0.1699

Data Index: 1456456 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.4836. Min Act: -0.1700

Data Index: 116284 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.4487. Min Act: -0.1700

Data Index: 1419703 (Python Code)

Max Activating Token Index: 458

Text #6

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.4304. Min Act: -0.1700

Data Index: 994245 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.4013. Min Act: -0.1694

Data Index: 1429365 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3907. Min Act: -0.1700

Data Index: 470806 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3760. Min Act: -0.1653

Data Index: 1592100 (Python Code)

Max Activating Token Index: 966

Text #10

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3834. Min Act: -0.1699

Data Index: 1450570 (Python Code)

Max Activating Token Index: 310

Text #11

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3619. Min Act: -0.1700

Data Index: 848053 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3644. Min Act: -0.1700

Data Index: 485433 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3622. Min Act: -0.1700

Data Index: 1287080 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3910. Min Act: -0.1700

Data Index: 369916 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3236. Min Act: -0.1699

Data Index: 122035 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3284. Min Act: -0.1659

Data Index: 187079 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3596. Min Act: -0.1700

Data Index: 1157422 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3489. Min Act: -0.1700

Data Index: 260129 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 3.5689. Min Range: -3.5689

Max Act: 3.3018. Min Act: -0.1698

Data Index: 1038500 (C4 (Web Text))

Max Activating Token Index: 70