Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1816 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.4763. Min Act: -0.1700

Data Index: 1492295 (Python Code)

Max Activating Token Index: 848

Text #1

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.4607. Min Act: -0.1700

Data Index: 1652188 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.3352. Min Act: -0.1700

Data Index: 1638272 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.2723. Min Act: -0.1697

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.1465. Min Act: -0.1700

Data Index: 1569892 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.1308. Min Act: -0.1700

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.0677. Min Act: -0.1700

Data Index: 1478717 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.0045. Min Act: -0.1700

Data Index: 1604509 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 3.4763. Min Range: -3.4763

Max Act: 3.0045. Min Act: -0.1700

Data Index: 169061 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9887. Min Act: -0.1700

Data Index: 1430150 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9571. Min Act: -0.1700

Data Index: 969026 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9571. Min Act: -0.1700

Data Index: 1361343 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9412. Min Act: -0.1700

Data Index: 1536826 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9412. Min Act: -0.1700

Data Index: 1505082 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9254. Min Act: -0.1700

Data Index: 1512797 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.9095. Min Act: -0.1700

Data Index: 1368707 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.8778. Min Act: -0.1700

Data Index: 1481986 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.8619. Min Act: -0.1700

Data Index: 1148188 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.8301. Min Act: -0.1700

Data Index: 493390 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 3.4763. Min Range: -3.4763

Max Act: 2.8301. Min Act: -0.1700

Data Index: 1461938 (Python Code)

Max Activating Token Index: 12