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

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

Neuron 2031 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: 3.4048. Min Range: -3.4048

Max Act: 3.4048. Min Act: -0.1700

Data Index: 820467 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3734. Min Act: -0.1700

Data Index: 706151 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3891. Min Act: -0.1700

Data Index: 159555 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3734. Min Act: -0.1699

Data Index: 975421 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3577. Min Act: -0.1700

Data Index: 1185511 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3577. Min Act: -0.1700

Data Index: 948896 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3577. Min Act: -0.1700

Data Index: 148876 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3421. Min Act: -0.1700

Data Index: 388989 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3264. Min Act: -0.1700

Data Index: 754378 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3264. Min Act: -0.1700

Data Index: 652622 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3421. Min Act: -0.1700

Data Index: 1312946 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1240368 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3264. Min Act: -0.1700

Data Index: 169300 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3107. Min Act: -0.1700

Data Index: 903958 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3264. Min Act: -0.1700

Data Index: 566850 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3107. Min Act: -0.1700

Data Index: 965641 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.2949. Min Act: -0.1700

Data Index: 1083322 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3107. Min Act: -0.1700

Data Index: 946938 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3107. Min Act: -0.1700

Data Index: 217843 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.4048. Min Range: -3.4048

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1025340 (C4 (Web Text))

Max Activating Token Index: 923