Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.2792. Min Act: -0.1700

Data Index: 556819 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.2167. Min Act: -0.1700

Data Index: 570688 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.0917. Min Act: -0.1700

Data Index: 224445 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.0605. Min Act: -0.1700

Data Index: 753621 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.0292. Min Act: -0.1700

Data Index: 148579 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9980. Min Act: -0.1700

Data Index: 886641 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9980. Min Act: -0.1700

Data Index: 339338 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9980. Min Act: -0.1700

Data Index: 72043 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 5.2792. Min Range: -5.2792

Max Act: 5.0292. Min Act: -0.1700

Data Index: 1027170 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9667. Min Act: -0.1700

Data Index: 1004645 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9667. Min Act: -0.1700

Data Index: 1181963 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9355. Min Act: -0.1700

Data Index: 1033658 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9355. Min Act: -0.1700

Data Index: 519016 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9355. Min Act: -0.1700

Data Index: 853574 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9667. Min Act: -0.1700

Data Index: 219104 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9355. Min Act: -0.1700

Data Index: 146071 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9042. Min Act: -0.1700

Data Index: 486256 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9042. Min Act: -0.1700

Data Index: 630756 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.9355. Min Act: -0.1700

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 5.2792. Min Range: -5.2792

Max Act: 4.8417. Min Act: -0.1700

Data Index: 758304 (C4 (Web Text))

Max Activating Token Index: 695