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

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

Neuron 1547 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: 4.1686. Min Range: -4.1686

Max Act: 4.1686. Min Act: -0.1700

Data Index: 364321 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.9966. Min Act: -0.1700

Data Index: 374934 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.9185. Min Act: -0.1700

Data Index: 311603 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.8872. Min Act: -0.1700

Data Index: 608811 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.9028. Min Act: -0.1700

Data Index: 1083900 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.8872. Min Act: -0.1700

Data Index: 669715 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7308. Min Act: -0.1700

Data Index: 990206 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7777. Min Act: -0.1700

Data Index: 595004 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7308. Min Act: -0.1700

Data Index: 1217481 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6682. Min Act: -0.1700

Data Index: 481675 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6839. Min Act: -0.1700

Data Index: 696952 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6995. Min Act: -0.1700

Data Index: 65425 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6995. Min Act: -0.1700

Data Index: 232084 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7151. Min Act: -0.1700

Data Index: 326643 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7464. Min Act: -0.1700

Data Index: 233502 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7151. Min Act: -0.1700

Data Index: 1104762 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6995. Min Act: -0.1700

Data Index: 376179 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7151. Min Act: -0.1700

Data Index: 225257 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6212. Min Act: -0.1700

Data Index: 158614 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6682. Min Act: -0.1700

Data Index: 130481 (C4 (Web Text))

Max Activating Token Index: 839