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

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

Neuron 530 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: 3.9893. Min Range: -3.9893

Max Act: 3.9737. Min Act: -0.1700

Data Index: 1189813 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9893. Min Act: -0.1699

Data Index: 400142 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9581. Min Act: -0.1700

Data Index: 409167 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9737. Min Act: -0.1700

Data Index: 858475 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9893. Min Act: -0.1700

Data Index: 845245 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9581. Min Act: -0.1700

Data Index: 608938 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9424. Min Act: -0.1700

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9424. Min Act: -0.1700

Data Index: 140314 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9424. Min Act: -0.1700

Data Index: 479750 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9268. Min Act: -0.1700

Data Index: 1197755 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9424. Min Act: -0.1700

Data Index: 642280 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9424. Min Act: -0.1700

Data Index: 432092 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9268. Min Act: -0.1700

Data Index: 729969 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9112. Min Act: -0.1700

Data Index: 820183 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9112. Min Act: -0.1700

Data Index: 222411 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9268. Min Act: -0.1700

Data Index: 132278 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9268. Min Act: -0.1700

Data Index: 108475 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9112. Min Act: -0.1700

Data Index: 244070 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8799. Min Act: -0.1700

Data Index: 1340019 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8642. Min Act: -0.1700

Data Index: 560952 (C4 (Web Text))

Max Activating Token Index: 694