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

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

Neuron 1974 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: 3.4516. Min Range: -3.4516

Max Act: 3.4516. Min Act: -0.1700

Data Index: 470750 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.4516. Min Act: -0.1700

Data Index: 1157657 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3889. Min Act: -0.1700

Data Index: 612872 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3889. Min Act: -0.1700

Data Index: 1142141 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3889. Min Act: -0.1700

Data Index: 812250 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3732. Min Act: -0.1700

Data Index: 442023 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3732. Min Act: -0.1700

Data Index: 994612 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3732. Min Act: -0.1700

Data Index: 570220 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1223639 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3575. Min Act: -0.1700

Data Index: 212152 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3261. Min Act: -0.1700

Data Index: 1298571 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3261. Min Act: -0.1700

Data Index: 789615 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3261. Min Act: -0.1700

Data Index: 1110114 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3104. Min Act: -0.1700

Data Index: 570225 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3104. Min Act: -0.1700

Data Index: 227752 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.3104. Min Act: -0.1700

Data Index: 486445 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.2947. Min Act: -0.1700

Data Index: 869978 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.2947. Min Act: -0.1700

Data Index: 888757 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.2790. Min Act: -0.1700

Data Index: 5586 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.4516. Min Range: -3.4516

Max Act: 3.2790. Min Act: -0.1700

Data Index: 1031587 (C4 (Web Text))

Max Activating Token Index: 169