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

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

Neuron 1280 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.5647. Min Act: -0.1700

Data Index: 432508 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.5334. Min Act: -0.1700

Data Index: 1073619 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.5020. Min Act: -0.1700

Data Index: 224642 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.4550. Min Act: -0.1700

Data Index: 1150455 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.4707. Min Act: -0.1700

Data Index: 349049 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.4550. Min Act: -0.1700

Data Index: 408997 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3923. Min Act: -0.1700

Data Index: 1099831 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3923. Min Act: -0.1700

Data Index: 221736 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3609. Min Act: -0.1700

Data Index: 1008475 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3609. Min Act: -0.1700

Data Index: 1213163 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3452. Min Act: -0.1700

Data Index: 53647 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3452. Min Act: -0.1700

Data Index: 223541 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3138. Min Act: -0.1700

Data Index: 998361 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3295. Min Act: -0.1700

Data Index: 1120842 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.2510. Min Act: -0.1700

Data Index: 802256 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.2981. Min Act: -0.1700

Data Index: 1092241 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3138. Min Act: -0.1700

Data Index: 35026 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3138. Min Act: -0.1700

Data Index: 228130 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.2824. Min Act: -0.1700

Data Index: 766204 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 3.5647. Min Range: -3.5647

Max Act: 3.3138. Min Act: -0.1700

Data Index: 618136 (C4 (Web Text))

Max Activating Token Index: 179