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

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

Neuron 815 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: 3.4820. Min Range: -3.4820

Max Act: 3.4820. Min Act: -0.1700

Data Index: 1368502 (Python Code)

Max Activating Token Index: 845

Text #1

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4193. Min Act: -0.1700

Data Index: 1569074 (Python Code)

Max Activating Token Index: 257

Text #2

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4036. Min Act: -0.1700

Data Index: 402342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1434319 (Python Code)

Max Activating Token Index: 948

Text #4

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3408. Min Act: -0.1700

Data Index: 1488312 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3251. Min Act: -0.1700

Data Index: 595395 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2937. Min Act: -0.1700

Data Index: 1489917 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3094. Min Act: -0.1700

Data Index: 1619866 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2623. Min Act: -0.1700

Data Index: 1606768 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2937. Min Act: -0.1700

Data Index: 1454366 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2780. Min Act: -0.1700

Data Index: 1430652 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2937. Min Act: -0.1700

Data Index: 1489694 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2780. Min Act: -0.1700

Data Index: 568041 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1604037 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2308. Min Act: -0.1700

Data Index: 1382998 (Python Code)

Max Activating Token Index: 849

Text #15

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2623. Min Act: -0.1700

Data Index: 1384598 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2623. Min Act: -0.1700

Data Index: 1459040 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1506476 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2623. Min Act: -0.1700

Data Index: 1590745 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.2151. Min Act: -0.1700

Data Index: 1598431 (Python Code)

Max Activating Token Index: 138