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

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

Neuron 1761 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: 3.5944. Min Range: -3.5944

Max Act: 3.5788. Min Act: -0.1700

Data Index: 1066865 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5944. Min Act: -0.1700

Data Index: 284699 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5474. Min Act: -0.1700

Data Index: 612422 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5631. Min Act: -0.1700

Data Index: 36748 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5318. Min Act: -0.1700

Data Index: 1186500 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5318. Min Act: -0.1700

Data Index: 713024 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5318. Min Act: -0.1700

Data Index: 613472 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5631. Min Act: -0.1700

Data Index: 444227 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5318. Min Act: -0.1700

Data Index: 934238 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5631. Min Act: -0.1700

Data Index: 97121 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5004. Min Act: -0.1700

Data Index: 846192 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5004. Min Act: -0.1700

Data Index: 899255 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5004. Min Act: -0.1700

Data Index: 594137 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5004. Min Act: -0.1700

Data Index: 537964 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5318. Min Act: -0.1700

Data Index: 973708 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.4691. Min Act: -0.1700

Data Index: 486734 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.4848. Min Act: -0.1700

Data Index: 55929 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.5161. Min Act: -0.1700

Data Index: 518583 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.4848. Min Act: -0.1700

Data Index: 633355 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 3.5944. Min Range: -3.5944

Max Act: 3.4691. Min Act: -0.1700

Data Index: 78414 (C4 (Web Text))

Max Activating Token Index: 696