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

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

Neuron 1544 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: 3.7957. Min Range: -3.7957

Max Act: 3.7957. Min Act: -0.1700

Data Index: 807457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5766. Min Act: -0.1700

Data Index: 193530 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.6705. Min Act: -0.1700

Data Index: 1612420 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5922. Min Act: -0.1700

Data Index: 238739 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5922. Min Act: -0.1700

Data Index: 592102 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5922. Min Act: -0.1700

Data Index: 1176463 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5766. Min Act: -0.1700

Data Index: 358076 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5922. Min Act: -0.1700

Data Index: 1280697 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5609. Min Act: -0.1700

Data Index: 1248869 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5766. Min Act: -0.1700

Data Index: 95369 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5766. Min Act: -0.1700

Data Index: 831370 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4826. Min Act: -0.1700

Data Index: 337320 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4826. Min Act: -0.1700

Data Index: 278620 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.5139. Min Act: -0.1700

Data Index: 562444 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4826. Min Act: -0.1700

Data Index: 1299569 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4669. Min Act: -0.1700

Data Index: 1323099 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4826. Min Act: -0.1700

Data Index: 85860 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4669. Min Act: -0.1700

Data Index: 442443 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4826. Min Act: -0.1700

Data Index: 307201 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.7957. Min Range: -3.7957

Max Act: 3.4512. Min Act: -0.1700

Data Index: 593572 (C4 (Web Text))

Max Activating Token Index: 315