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

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

Neuron 852 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.6033. Min Act: -0.1700

Data Index: 1446684 (Python Code)

Max Activating Token Index: 167

Text #1

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.5408. Min Act: -0.1700

Data Index: 1484057 (Python Code)

Max Activating Token Index: 852

Text #2

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.5720. Min Act: -0.1700

Data Index: 1433895 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.5408. Min Act: -0.1700

Data Index: 1382533 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1374888 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.5408. Min Act: -0.1700

Data Index: 605825 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1401595 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.6033. Min Act: -0.1700

Data Index: 1644338 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.5095. Min Act: -0.1700

Data Index: 863483 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.5720. Min Act: -0.1700

Data Index: 1362856 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4470. Min Act: -0.1700

Data Index: 684064 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4783. Min Act: -0.1700

Data Index: 281444 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4470. Min Act: -0.1700

Data Index: 583290 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1571136 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.3845. Min Act: -0.1700

Data Index: 1601667 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4470. Min Act: -0.1700

Data Index: 299938 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4158. Min Act: -0.1700

Data Index: 680135 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4783. Min Act: -0.1700

Data Index: 167792 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4158. Min Act: -0.1700

Data Index: 314178 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 5.6033. Min Range: -5.6033

Max Act: 5.4158. Min Act: -0.1700

Data Index: 1384400 (Python Code)

Max Activating Token Index: 736