Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 844 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.4137. Min Act: -0.1700

Data Index: 602260 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.2575. Min Act: -0.1700

Data Index: 1103577 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.2575. Min Act: -0.1700

Data Index: 675182 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1637. Min Act: -0.1700

Data Index: 1128782 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1637. Min Act: -0.1700

Data Index: 578043 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1637. Min Act: -0.1700

Data Index: 780593 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.0387. Min Act: -0.1700

Data Index: 1270615 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1325. Min Act: -0.1700

Data Index: 1148988 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1325. Min Act: -0.1700

Data Index: 674595 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1325. Min Act: -0.1700

Data Index: 943994 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1325. Min Act: -0.1700

Data Index: 252687 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1012. Min Act: -0.1700

Data Index: 1321355 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1012. Min Act: -0.1700

Data Index: 45873 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.0700. Min Act: -0.1700

Data Index: 953289 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1012. Min Act: -0.1700

Data Index: 855090 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.0075. Min Act: -0.1700

Data Index: 630683 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.0700. Min Act: -0.1700

Data Index: 204867 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.0387. Min Act: -0.1700

Data Index: 1331141 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.0387. Min Act: -0.1700

Data Index: 272625 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 5.4137. Min Range: -5.4137

Max Act: 5.1012. Min Act: -0.1700

Data Index: 180059 (C4 (Web Text))

Max Activating Token Index: 309