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

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

Neuron 144 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9418. Min Act: -0.1700

Data Index: 690922 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9418. Min Act: -0.1700

Data Index: 1029457 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9418. Min Act: -0.1700

Data Index: 460970 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9731. Min Act: -0.1700

Data Index: 289122 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 545369 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 126885 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9418. Min Act: -0.1700

Data Index: 486205 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9106. Min Act: -0.1700

Data Index: 692448 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.9106. Min Act: -0.1700

Data Index: 1332554 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 1108952 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 825183 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 1205272 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 1326804 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 491174 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 328824 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 201099 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 219675 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8793. Min Act: -0.1700

Data Index: 64073 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.7854. Min Act: -0.1700

Data Index: 959094 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 3.9731. Min Range: -3.9731

Max Act: 3.8480. Min Act: -0.1700

Data Index: 339246 (C4 (Web Text))

Max Activating Token Index: 349