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

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

Neuron 1463 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: 3.8104. Min Range: -3.8104

Max Act: 3.8104. Min Act: -0.1700

Data Index: 860752 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.7478. Min Act: -0.1700

Data Index: 981855 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.7165. Min Act: -0.1700

Data Index: 1329283 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.7165. Min Act: -0.1700

Data Index: 525218 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6695. Min Act: -0.1700

Data Index: 846912 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.7165. Min Act: -0.1700

Data Index: 354381 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6852. Min Act: -0.1700

Data Index: 646487 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6852. Min Act: -0.1700

Data Index: 1327341 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6539. Min Act: -0.1700

Data Index: 573685 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6226. Min Act: -0.1700

Data Index: 461295 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6382. Min Act: -0.1700

Data Index: 388766 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1109995 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1266979 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1249417 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6226. Min Act: -0.1700

Data Index: 533684 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1333139 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6069. Min Act: -0.1700

Data Index: 1203748 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.5913. Min Act: -0.1700

Data Index: 527528 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6069. Min Act: -0.1700

Data Index: 374581 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.8104. Min Range: -3.8104

Max Act: 3.6852. Min Act: -0.1700

Data Index: 239420 (C4 (Web Text))

Max Activating Token Index: 411