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

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

Neuron 1419 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6790. Min Act: -0.1700

Data Index: 614716 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6164. Min Act: -0.1700

Data Index: 773796 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4754. Min Act: -0.1700

Data Index: 102077 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5381. Min Act: -0.1700

Data Index: 856616 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5224. Min Act: -0.1700

Data Index: 1238032 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5381. Min Act: -0.1700

Data Index: 72023 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5537. Min Act: -0.1700

Data Index: 924324 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4127. Min Act: -0.1700

Data Index: 433589 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4911. Min Act: -0.1700

Data Index: 891352 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4911. Min Act: -0.1700

Data Index: 147411 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4127. Min Act: -0.1700

Data Index: 502826 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4127. Min Act: -0.1700

Data Index: 113320 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4597. Min Act: -0.1700

Data Index: 226924 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.3499. Min Act: -0.1700

Data Index: 720023 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.3499. Min Act: -0.1700

Data Index: 89387 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.3813. Min Act: -0.1700

Data Index: 970684 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4284. Min Act: -0.1700

Data Index: 688145 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.3970. Min Act: -0.1700

Data Index: 627819 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.4284. Min Act: -0.1700

Data Index: 533003 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.3499. Min Act: -0.1700

Data Index: 788855 (C4 (Web Text))

Max Activating Token Index: 587