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

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

Neuron 1099 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1977. Min Act: -0.1700

Data Index: 1154009 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.1352. Min Act: -0.1700

Data Index: 617875 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 5.1977. Min Range: -5.1977

Max Act: 5.0727. Min Act: -0.1700

Data Index: 923872 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8852. Min Act: -0.1700

Data Index: 1641835 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8852. Min Act: -0.1700

Data Index: 1267129 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8852. Min Act: -0.1700

Data Index: 1224084 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8852. Min Act: -0.1700

Data Index: 804791 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8227. Min Act: -0.1700

Data Index: 1355295 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8227. Min Act: -0.1700

Data Index: 1052976 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.8227. Min Act: -0.1700

Data Index: 1512391 (Python Code)

Max Activating Token Index: 792

Text #10

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.7602. Min Act: -0.1700

Data Index: 1496056 (Python Code)

Max Activating Token Index: 652

Text #11

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.7602. Min Act: -0.1700

Data Index: 962027 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.7602. Min Act: -0.1700

Data Index: 616735 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.6976. Min Act: -0.1700

Data Index: 145678 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.6976. Min Act: -0.1700

Data Index: 1031992 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.5726. Min Act: -0.1700

Data Index: 139962 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.5726. Min Act: -0.1700

Data Index: 1572021 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.6351. Min Act: -0.1700

Data Index: 1478981 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.5726. Min Act: -0.1700

Data Index: 1441020 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 5.1977. Min Range: -5.1977

Max Act: 4.5101. Min Act: -0.1700

Data Index: 1635716 (Python Code)

Max Activating Token Index: 852