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

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

Neuron 416 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.2738. Min Act: -0.1700

Data Index: 138503 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.2110. Min Act: -0.1700

Data Index: 648177 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.1480. Min Act: -0.1700

Data Index: 5186 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0849. Min Act: -0.1700

Data Index: 634360 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.1165. Min Act: -0.1700

Data Index: 900191 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0849. Min Act: -0.1700

Data Index: 837357 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0849. Min Act: -0.1700

Data Index: 608477 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0534. Min Act: -0.1700

Data Index: 1195143 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0534. Min Act: -0.1700

Data Index: 1359455 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0849. Min Act: -0.1700

Data Index: 900552 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0218. Min Act: -0.1700

Data Index: 498346 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0849. Min Act: -0.1700

Data Index: 1109352 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0534. Min Act: -0.1700

Data Index: 48987 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.2738. Min Range: -3.2738

Max Act: 2.9902. Min Act: -0.1700

Data Index: 1463393 (Python Code)

Max Activating Token Index: 123

Text #14

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0218. Min Act: -0.1700

Data Index: 1132597 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0060. Min Act: -0.1700

Data Index: 480992 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0218. Min Act: -0.1700

Data Index: 1076172 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0218. Min Act: -0.1700

Data Index: 78029 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0060. Min Act: -0.1700

Data Index: 387067 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 3.2738. Min Range: -3.2738

Max Act: 3.0534. Min Act: -0.1700

Data Index: 111998 (C4 (Web Text))

Max Activating Token Index: 894