Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 17 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2857. Min Range: -3.2857

Max Act: 3.2857. Min Act: -0.1700

Data Index: 1440303 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 3.2857. Min Range: -3.2857

Max Act: 3.2228. Min Act: -0.1700

Data Index: 1372419 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 3.2857. Min Range: -3.2857

Max Act: 3.1126. Min Act: -0.1700

Data Index: 1546450 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 3.2857. Min Range: -3.2857

Max Act: 3.0653. Min Act: -0.1700

Data Index: 1442240 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 3.2857. Min Range: -3.2857

Max Act: 3.0179. Min Act: -0.1700

Data Index: 1379949 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.9863. Min Act: -0.1700

Data Index: 1545227 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.9388. Min Act: -0.1700

Data Index: 1416526 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8913. Min Act: -0.1700

Data Index: 1471241 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8913. Min Act: -0.1700

Data Index: 1652355 (Python Code)

Max Activating Token Index: 119

Text #9

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1596305 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1530522 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1538256 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1440046 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8436. Min Act: -0.1700

Data Index: 1636603 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8595. Min Act: -0.1700

Data Index: 1427256 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8436. Min Act: -0.1700

Data Index: 1445877 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8436. Min Act: -0.1700

Data Index: 1562950 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8436. Min Act: -0.1700

Data Index: 1424804 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8436. Min Act: -0.1700

Data Index: 1392447 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 3.2857. Min Range: -3.2857

Max Act: 2.8436. Min Act: -0.1700

Data Index: 1515181 (Python Code)

Max Activating Token Index: 45