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

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

Neuron 1792 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: 3.3242. Min Range: -3.3242

Max Act: 3.3242. Min Act: -0.1700

Data Index: 603098 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.2300. Min Act: -0.1700

Data Index: 457787 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.1513. Min Act: -0.1700

Data Index: 1185062 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.1040. Min Act: -0.1700

Data Index: 1132012 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0567. Min Act: -0.1700

Data Index: 709714 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0883. Min Act: -0.1700

Data Index: 1318376 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0567. Min Act: -0.1700

Data Index: 535788 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.1040. Min Act: -0.1700

Data Index: 633703 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0567. Min Act: -0.1700

Data Index: 574203 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0409. Min Act: -0.1700

Data Index: 261597 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.3242. Min Range: -3.3242

Max Act: 2.9619. Min Act: -0.1700

Data Index: 862191 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0409. Min Act: -0.1700

Data Index: 1154764 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0251. Min Act: -0.1700

Data Index: 223421 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 3.3242. Min Range: -3.3242

Max Act: 2.9935. Min Act: -0.1700

Data Index: 183108 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0409. Min Act: -0.1700

Data Index: 169494 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0409. Min Act: -0.1700

Data Index: 406628 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.3242. Min Range: -3.3242

Max Act: 2.9619. Min Act: -0.1700

Data Index: 1324077 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0409. Min Act: -0.1700

Data Index: 1353033 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 3.3242. Min Range: -3.3242

Max Act: 3.0409. Min Act: -0.1700

Data Index: 117578 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.3242. Min Range: -3.3242

Max Act: 2.9777. Min Act: -0.1700

Data Index: 127003 (C4 (Web Text))

Max Activating Token Index: 144