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

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

Neuron 298 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.5331. Min Act: -0.1700

Data Index: 1511588 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1370655 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.4081. Min Act: -0.1700

Data Index: 1378620 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3769. Min Act: -0.1700

Data Index: 1597734 (Python Code)

Max Activating Token Index: 693

Text #4

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.4394. Min Act: -0.1700

Data Index: 1508902 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.4394. Min Act: -0.1700

Data Index: 1593387 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3144. Min Act: -0.1700

Data Index: 1379531 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3769. Min Act: -0.1700

Data Index: 1443319 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3456. Min Act: -0.1700

Data Index: 1413796 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3456. Min Act: -0.1700

Data Index: 1635724 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.4081. Min Act: -0.1700

Data Index: 1532042 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3769. Min Act: -0.1700

Data Index: 1407847 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3769. Min Act: -0.1700

Data Index: 1546557 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.2831. Min Act: -0.1700

Data Index: 1469405 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3144. Min Act: -0.1700

Data Index: 1582523 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3144. Min Act: -0.1700

Data Index: 1552519 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3456. Min Act: -0.1700

Data Index: 1645734 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.2831. Min Act: -0.1700

Data Index: 1638826 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3144. Min Act: -0.1700

Data Index: 1453408 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 5.5331. Min Range: -5.5331

Max Act: 5.3456. Min Act: -0.1700

Data Index: 1525701 (Python Code)

Max Activating Token Index: 144