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

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

Neuron 1824 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: 3.3803. Min Range: -3.3803

Max Act: 3.3803. Min Act: -0.1700

Data Index: 459802 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.2076. Min Act: -0.1700

Data Index: 45703 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.1918. Min Act: -0.1700

Data Index: 184270 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.1603. Min Act: -0.1700

Data Index: 1211991 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.1603. Min Act: -0.1700

Data Index: 352301 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.1131. Min Act: -0.1700

Data Index: 968669 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0973. Min Act: -0.1700

Data Index: 794002 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.1131. Min Act: -0.1700

Data Index: 704090 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0815. Min Act: -0.1700

Data Index: 1005561 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0815. Min Act: -0.1700

Data Index: 972608 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.1288. Min Act: -0.1700

Data Index: 1302121 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0500. Min Act: -0.1700

Data Index: 674481 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0658. Min Act: -0.1700

Data Index: 159880 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0658. Min Act: -0.1700

Data Index: 214583 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0342. Min Act: -0.1700

Data Index: 888313 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0500. Min Act: -0.1700

Data Index: 292522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0500. Min Act: -0.1700

Data Index: 1014788 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0342. Min Act: -0.1700

Data Index: 241506 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0500. Min Act: -0.1700

Data Index: 995278 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 3.3803. Min Range: -3.3803

Max Act: 3.0342. Min Act: -0.1700

Data Index: 194298 (C4 (Web Text))

Max Activating Token Index: 1018