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

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

Neuron 1712 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.3024. Min Act: -0.1700

Data Index: 49019 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2867. Min Act: -0.1700

Data Index: 994804 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2553. Min Act: -0.1700

Data Index: 501179 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2867. Min Act: -0.1700

Data Index: 1199175 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2710. Min Act: -0.1700

Data Index: 352892 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2553. Min Act: -0.1700

Data Index: 1315785 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1924. Min Act: -0.1700

Data Index: 724204 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2396. Min Act: -0.1700

Data Index: 749922 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1337252 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2396. Min Act: -0.1700

Data Index: 630169 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2238. Min Act: -0.1700

Data Index: 534982 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2238. Min Act: -0.1700

Data Index: 79337 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1924. Min Act: -0.1700

Data Index: 104337 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2238. Min Act: -0.1700

Data Index: 85891 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2553. Min Act: -0.1700

Data Index: 953988 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2081. Min Act: -0.1700

Data Index: 373768 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2081. Min Act: -0.1700

Data Index: 559685 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1766. Min Act: -0.1700

Data Index: 317772 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.2238. Min Act: -0.1700

Data Index: 749324 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.3024. Min Range: -3.3024

Max Act: 3.1924. Min Act: -0.1700

Data Index: 1085218 (C4 (Web Text))

Max Activating Token Index: 589