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

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

Neuron 2033 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.4148. Min Act: -0.1700

Data Index: 33218 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.3523. Min Act: -0.1700

Data Index: 1185290 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.3836. Min Act: -0.1700

Data Index: 634872 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.3211. Min Act: -0.1700

Data Index: 626912 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2586. Min Act: -0.1700

Data Index: 832122 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.3523. Min Act: -0.1700

Data Index: 1299384 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2586. Min Act: -0.1700

Data Index: 730040 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2586. Min Act: -0.1700

Data Index: 720498 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.3211. Min Act: -0.1700

Data Index: 278365 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2273. Min Act: -0.1700

Data Index: 622794 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2898. Min Act: -0.1700

Data Index: 170551 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2898. Min Act: -0.1700

Data Index: 1239015 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2273. Min Act: -0.1700

Data Index: 1191587 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2273. Min Act: -0.1700

Data Index: 199832 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2273. Min Act: -0.1700

Data Index: 78530 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2273. Min Act: -0.1700

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.1648. Min Act: -0.1700

Data Index: 1256442 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.2273. Min Act: -0.1700

Data Index: 344257 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.1648. Min Act: -0.1700

Data Index: 783189 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 5.4148. Min Range: -5.4148

Max Act: 5.1961. Min Act: -0.1700

Data Index: 313548 (C4 (Web Text))

Max Activating Token Index: 770