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

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

Neuron 1829 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: 3.5928. Min Range: -3.5928

Max Act: 3.5928. Min Act: -0.1700

Data Index: 1009569 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5615. Min Act: -0.1700

Data Index: 1234569 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5458. Min Act: -0.1700

Data Index: 767712 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5615. Min Act: -0.1700

Data Index: 1176448 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5301. Min Act: -0.1700

Data Index: 1054415 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5145. Min Act: -0.1700

Data Index: 726042 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.5145. Min Act: -0.1700

Data Index: 961040 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4988. Min Act: -0.1700

Data Index: 1093213 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4988. Min Act: -0.1700

Data Index: 434192 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4048. Min Act: -0.1700

Data Index: 696842 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4204. Min Act: -0.1700

Data Index: 247672 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.3891. Min Act: -0.1700

Data Index: 758202 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4518. Min Act: -0.1700

Data Index: 1235797 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4361. Min Act: -0.1700

Data Index: 313768 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4518. Min Act: -0.1700

Data Index: 518161 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4361. Min Act: -0.1700

Data Index: 1284057 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4675. Min Act: -0.1700

Data Index: 41144 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4518. Min Act: -0.1700

Data Index: 150058 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4204. Min Act: -0.1700

Data Index: 79897 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 3.5928. Min Range: -3.5928

Max Act: 3.4204. Min Act: -0.1700

Data Index: 582078 (C4 (Web Text))

Max Activating Token Index: 462