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

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

Neuron 1517 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: 5.5686. Min Range: -5.5686

Max Act: 5.5686. Min Act: -0.1700

Data Index: 39097 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.3186. Min Act: -0.1700

Data Index: 720107 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.3498. Min Act: -0.1700

Data Index: 1124714 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.2561. Min Act: -0.1700

Data Index: 162555 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.2248. Min Act: -0.1699

Data Index: 1210626 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.1623. Min Act: -0.1700

Data Index: 201700 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.1936. Min Act: -0.1700

Data Index: 22902 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0998. Min Act: -0.1700

Data Index: 548300 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0998. Min Act: -0.1700

Data Index: 874274 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.1623. Min Act: -0.1700

Data Index: 505570 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0373. Min Act: -0.1700

Data Index: 178777 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0061. Min Act: -0.1700

Data Index: 216686 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0061. Min Act: -0.1700

Data Index: 1225803 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0061. Min Act: -0.1700

Data Index: 1120760 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0373. Min Act: -0.1700

Data Index: 390287 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0373. Min Act: -0.1700

Data Index: 842023 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0373. Min Act: -0.1700

Data Index: 819634 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0061. Min Act: -0.1700

Data Index: 310643 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0373. Min Act: -0.1700

Data Index: 965738 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 5.5686. Min Range: -5.5686

Max Act: 5.0061. Min Act: -0.1700

Data Index: 966412 (C4 (Web Text))

Max Activating Token Index: 206