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

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

Neuron 1209 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: 5.5051. Min Range: -5.5051

Max Act: 5.5051. Min Act: -0.1700

Data Index: 652717 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.5051. Min Act: -0.1700

Data Index: 627739 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.4426. Min Act: -0.1700

Data Index: 462489 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3801. Min Act: -0.1700

Data Index: 538884 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.4113. Min Act: -0.1700

Data Index: 1170974 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3801. Min Act: -0.1700

Data Index: 983146 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 1294626 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 827888 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 1091824 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.2863. Min Act: -0.1700

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3801. Min Act: -0.1700

Data Index: 111867 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3176. Min Act: -0.1700

Data Index: 74772 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 1166010 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.2863. Min Act: -0.1700

Data Index: 848237 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3176. Min Act: -0.1700

Data Index: 561206 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 328391 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 1058854 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3176. Min Act: -0.1700

Data Index: 1197655 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.3488. Min Act: -0.1700

Data Index: 861172 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 5.5051. Min Range: -5.5051

Max Act: 5.2863. Min Act: -0.1700

Data Index: 1283168 (C4 (Web Text))

Max Activating Token Index: 883