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

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

Neuron 838 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: 3.3889. Min Range: -3.3889

Max Act: 3.3889. Min Act: -0.1700

Data Index: 308088 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3575. Min Act: -0.1700

Data Index: 251213 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3418. Min Act: -0.1700

Data Index: 465735 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3575. Min Act: -0.1700

Data Index: 996395 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3261. Min Act: -0.1700

Data Index: 1319482 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3261. Min Act: -0.1700

Data Index: 249563 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3261. Min Act: -0.1700

Data Index: 24365 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.3104. Min Act: -0.1700

Data Index: 1282150 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1132633 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1289095 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1015796 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2790. Min Act: -0.1700

Data Index: 1002597 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2633. Min Act: -0.1700

Data Index: 729718 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2790. Min Act: -0.1700

Data Index: 1089547 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2790. Min Act: -0.1700

Data Index: 83314 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2633. Min Act: -0.1700

Data Index: 44684 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2790. Min Act: -0.1700

Data Index: 1343241 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2633. Min Act: -0.1700

Data Index: 450353 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2790. Min Act: -0.1700

Data Index: 174482 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 3.3889. Min Range: -3.3889

Max Act: 3.2475. Min Act: -0.1700

Data Index: 513649 (C4 (Web Text))

Max Activating Token Index: 122