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

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

Neuron 1489 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.9504. Min Act: -0.1700

Data Index: 1022944 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.9191. Min Act: -0.1700

Data Index: 439871 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.8566. Min Act: -0.1700

Data Index: 1312486 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.8253. Min Act: -0.1700

Data Index: 576299 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1085767 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7940. Min Act: -0.1700

Data Index: 1115593 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.8253. Min Act: -0.1700

Data Index: 992106 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7627. Min Act: -0.1700

Data Index: 879229 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7314. Min Act: -0.1700

Data Index: 304430 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7314. Min Act: -0.1700

Data Index: 1279634 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7314. Min Act: -0.1700

Data Index: 648508 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.6688. Min Act: -0.1700

Data Index: 646699 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7314. Min Act: -0.1700

Data Index: 1155232 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7314. Min Act: -0.1700

Data Index: 1142929 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7001. Min Act: -0.1700

Data Index: 408292 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7627. Min Act: -0.1700

Data Index: 580233 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7314. Min Act: -0.1700

Data Index: 428423 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7001. Min Act: -0.1700

Data Index: 148324 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.6375. Min Act: -0.1700

Data Index: 491292 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 3.9504. Min Range: -3.9504

Max Act: 3.7001. Min Act: -0.1700

Data Index: 1211515 (C4 (Web Text))

Max Activating Token Index: 11