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

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

Neuron 1957 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: 7.0472. Min Range: -7.0472

Max Act: 7.0472. Min Act: -0.1700

Data Index: 996448 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.8910. Min Act: -0.1700

Data Index: 755889 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.7660. Min Act: -0.1700

Data Index: 764574 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.7347. Min Act: -0.1700

Data Index: 1258067 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.6410. Min Act: -0.1700

Data Index: 407363 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.6097. Min Act: -0.1700

Data Index: 1084174 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.6097. Min Act: -0.1700

Data Index: 21385 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5472. Min Act: -0.1700

Data Index: 374778 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.6097. Min Act: -0.1700

Data Index: 18510 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5472. Min Act: -0.1700

Data Index: 1073736 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5785. Min Act: -0.1700

Data Index: 833612 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5160. Min Act: -0.1700

Data Index: 538041 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5160. Min Act: -0.1700

Data Index: 1001122 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.4847. Min Act: -0.1700

Data Index: 786481 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5160. Min Act: -0.1700

Data Index: 1292410 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.4535. Min Act: -0.1700

Data Index: 463684 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.4847. Min Act: -0.1700

Data Index: 631324 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5472. Min Act: -0.1700

Data Index: 405031 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.5160. Min Act: -0.1700

Data Index: 246478 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 7.0472. Min Range: -7.0472

Max Act: 6.4847. Min Act: -0.1700

Data Index: 1183338 (C4 (Web Text))

Max Activating Token Index: 408