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

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

Neuron 1059 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.2831. Min Act: -0.1700

Data Index: 1310468 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.1268. Min Act: -0.1700

Data Index: 692456 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0955. Min Act: -0.1700

Data Index: 791790 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0330. Min Act: -0.1700

Data Index: 117205 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0643. Min Act: -0.1700

Data Index: 108851 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0330. Min Act: -0.1700

Data Index: 344905 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0018. Min Act: -0.1700

Data Index: 248852 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0018. Min Act: -0.1700

Data Index: 1053067 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 4.2831. Min Range: -4.2831

Max Act: 4.0018. Min Act: -0.1700

Data Index: 235650 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1250513 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1312110 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9392. Min Act: -0.1700

Data Index: 455585 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 950855 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1058169 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1097382 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 547693 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1171524 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 569021 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 714858 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 4.2831. Min Range: -4.2831

Max Act: 3.9705. Min Act: -0.1700

Data Index: 366601 (C4 (Web Text))

Max Activating Token Index: 587