Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.4246. Min Act: -0.1700

Data Index: 1567636 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.4871. Min Act: -0.1700

Data Index: 1364876 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.4558. Min Act: -0.1700

Data Index: 1376436 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.4558. Min Act: -0.1700

Data Index: 1494624 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.3308. Min Act: -0.1700

Data Index: 1498658 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.3933. Min Act: -0.1700

Data Index: 1495759 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.3308. Min Act: -0.1700

Data Index: 1570241 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.2683. Min Act: -0.1700

Data Index: 1641768 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.2058. Min Act: -0.1700

Data Index: 1385296 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.2058. Min Act: -0.1699

Data Index: 1417699 (Python Code)

Max Activating Token Index: 140

Text #10

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.1433. Min Act: -0.1700

Data Index: 1404513 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.1433. Min Act: -0.1700

Data Index: 1596775 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.1746. Min Act: -0.1700

Data Index: 1422906 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.1433. Min Act: -0.1700

Data Index: 1430986 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.1433. Min Act: -0.1700

Data Index: 1421303 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.0808. Min Act: -0.1700

Data Index: 1615659 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.0183. Min Act: -0.1700

Data Index: 1505624 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.0496. Min Act: -0.1700

Data Index: 1436255 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.1121. Min Act: -0.1699

Data Index: 1505428 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 7.4871. Min Range: -7.4871

Max Act: 7.0183. Min Act: -0.1700

Data Index: 1498827 (Python Code)

Max Activating Token Index: 43