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

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

Neuron 1731 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: 3.8945. Min Range: -3.8945

Max Act: 3.8945. Min Act: -0.1700

Data Index: 53804 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8320. Min Act: -0.1700

Data Index: 907469 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.6129. Min Act: -0.1700

Data Index: 1359828 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.6286. Min Act: -0.1700

Data Index: 306884 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5816. Min Act: -0.1700

Data Index: 265613 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.6129. Min Act: -0.1700

Data Index: 935361 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.4719. Min Act: -0.1700

Data Index: 152755 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1165297 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5973. Min Act: -0.1700

Data Index: 702194 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5503. Min Act: -0.1700

Data Index: 466008 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5346. Min Act: -0.1700

Data Index: 386404 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5659. Min Act: -0.1700

Data Index: 235891 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5346. Min Act: -0.1700

Data Index: 386819 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5816. Min Act: -0.1700

Data Index: 529147 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5190. Min Act: -0.1700

Data Index: 1079006 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.4876. Min Act: -0.1700

Data Index: 2944 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5346. Min Act: -0.1700

Data Index: 1035015 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.4876. Min Act: -0.1700

Data Index: 174299 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5033. Min Act: -0.1700

Data Index: 291882 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.5033. Min Act: -0.1700

Data Index: 483428 (C4 (Web Text))

Max Activating Token Index: 936