Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1982 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.9435. Min Act: -0.1700

Data Index: 1492428 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1085806 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7402. Min Act: -0.1700

Data Index: 89541 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7089. Min Act: -0.1700

Data Index: 926429 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6619. Min Act: -0.1700

Data Index: 381227 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6150. Min Act: -0.1700

Data Index: 431080 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6306. Min Act: -0.1700

Data Index: 1405319 (Python Code)

Max Activating Token Index: 599

Text #7

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6619. Min Act: -0.1700

Data Index: 1163991 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6150. Min Act: -0.1700

Data Index: 426701 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6463. Min Act: -0.1700

Data Index: 1141867 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5993. Min Act: -0.1700

Data Index: 1135457 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5367. Min Act: -0.1700

Data Index: 991011 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5523. Min Act: -0.1700

Data Index: 153765 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5837. Min Act: -0.1700

Data Index: 426655 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5680. Min Act: -0.1700

Data Index: 1135838 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5680. Min Act: -0.1700

Data Index: 1310557 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5523. Min Act: -0.1700

Data Index: 905680 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5680. Min Act: -0.1700

Data Index: 906086 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5210. Min Act: -0.1700

Data Index: 201626 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5210. Min Act: -0.1700

Data Index: 103585 (C4 (Web Text))

Max Activating Token Index: 855