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

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

Neuron 804 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: 5.0038. Min Range: -5.0038

Max Act: 5.0038. Min Act: -0.1700

Data Index: 86459 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9726. Min Act: -0.1700

Data Index: 1169825 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9101. Min Act: -0.1700

Data Index: 239042 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9413. Min Act: -0.1700

Data Index: 989203 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9101. Min Act: -0.1700

Data Index: 622425 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9101. Min Act: -0.1700

Data Index: 449844 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8476. Min Act: -0.1700

Data Index: 1058188 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9101. Min Act: -0.1700

Data Index: 33848 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9101. Min Act: -0.1700

Data Index: 289188 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8788. Min Act: -0.1700

Data Index: 1273962 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8476. Min Act: -0.1700

Data Index: 797070 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8163. Min Act: -0.1700

Data Index: 584602 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8476. Min Act: -0.1700

Data Index: 1224486 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.9413. Min Act: -0.1700

Data Index: 141590 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8163. Min Act: -0.1700

Data Index: 567760 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8163. Min Act: -0.1700

Data Index: 735645 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8163. Min Act: -0.1700

Data Index: 946350 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8788. Min Act: -0.1700

Data Index: 21944 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8788. Min Act: -0.1700

Data Index: 14004 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 5.0038. Min Range: -5.0038

Max Act: 4.8788. Min Act: -0.1700

Data Index: 1355220 (C4 (Web Text))

Max Activating Token Index: 814