Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1331 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.1729. Min Range: -7.1729

Max Act: 7.1729. Min Act: -0.1700

Data Index: 17884 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 7.1729. Min Range: -7.1729

Max Act: 7.1104. Min Act: -0.1699

Data Index: 659193 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 7.1729. Min Range: -7.1729

Max Act: 7.1104. Min Act: -0.1699

Data Index: 470033 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 7.1729. Min Range: -7.1729

Max Act: 7.0167. Min Act: -0.1693

Data Index: 230271 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.9229. Min Act: -0.1700

Data Index: 340521 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.9542. Min Act: -0.1700

Data Index: 468232 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.9229. Min Act: -0.1700

Data Index: 559552 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.8917. Min Act: -0.1700

Data Index: 767172 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.8604. Min Act: -0.1700

Data Index: 680096 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.8292. Min Act: -0.1698

Data Index: 144522 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.8292. Min Act: -0.1700

Data Index: 770954 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.8292. Min Act: -0.1694

Data Index: 1219306 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7979. Min Act: -0.1700

Data Index: 969433 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7354. Min Act: -0.1700

Data Index: 1111030 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7667. Min Act: -0.1700

Data Index: 541424 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7042. Min Act: -0.1700

Data Index: 756581 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7354. Min Act: -0.1700

Data Index: 142841 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7354. Min Act: -0.1700

Data Index: 552339 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.6729. Min Act: -0.1700

Data Index: 147218 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 7.1729. Min Range: -7.1729

Max Act: 6.7354. Min Act: -0.1700

Data Index: 75641 (C4 (Web Text))

Max Activating Token Index: 893