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

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

Neuron 1166 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.4483. Min Act: -0.1700

Data Index: 1604867 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.4169. Min Act: -0.1700

Data Index: 1338171 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.4012. Min Act: -0.1700

Data Index: 1514105 (Python Code)

Max Activating Token Index: 954

Text #3

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.3855. Min Act: -0.1700

Data Index: 1442134 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2914. Min Act: -0.1700

Data Index: 1520436 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2756. Min Act: -0.1700

Data Index: 1360449 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2285. Min Act: -0.1700

Data Index: 1531049 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2442. Min Act: -0.1700

Data Index: 1468506 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2285. Min Act: -0.1700

Data Index: 1454562 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2285. Min Act: -0.1700

Data Index: 1628632 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2442. Min Act: -0.1700

Data Index: 1375425 (Python Code)

Max Activating Token Index: 184

Text #11

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.1970. Min Act: -0.1700

Data Index: 855022 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2128. Min Act: -0.1700

Data Index: 1562479 (Python Code)

Max Activating Token Index: 932

Text #13

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2128. Min Act: -0.1700

Data Index: 1593212 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.2128. Min Act: -0.1700

Data Index: 1503830 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.1970. Min Act: -0.1700

Data Index: 1632768 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.1970. Min Act: -0.1700

Data Index: 1469736 (Python Code)

Max Activating Token Index: 50

Text #17

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.1970. Min Act: -0.1700

Data Index: 1175931 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.1656. Min Act: -0.1700

Data Index: 1549250 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 3.4483. Min Range: -3.4483

Max Act: 3.1813. Min Act: -0.1700

Data Index: 1485882 (Python Code)

Max Activating Token Index: 170