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

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

Neuron 34 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: 3.9324. Min Range: -3.9324

Max Act: 3.9324. Min Act: -0.1700

Data Index: 241481 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7448. Min Act: -0.1700

Data Index: 498441 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7448. Min Act: -0.1700

Data Index: 895673 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7448. Min Act: -0.1700

Data Index: 1154274 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 1358334 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7448. Min Act: -0.1700

Data Index: 229239 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7761. Min Act: -0.1700

Data Index: 814053 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 262740 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6822. Min Act: -0.1700

Data Index: 401126 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6509. Min Act: -0.1700

Data Index: 532578 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 807556 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 809581 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7448. Min Act: -0.1700

Data Index: 557784 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 10427 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7448. Min Act: -0.1700

Data Index: 656730 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 821256 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 860234 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 894544 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7135. Min Act: -0.1700

Data Index: 164104 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6509. Min Act: -0.1700

Data Index: 689642 (C4 (Web Text))

Max Activating Token Index: 883