Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 388 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.3020. Min Act: -0.1700

Data Index: 1071460 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0817. Min Act: -0.1700

Data Index: 496743 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0817. Min Act: -0.1700

Data Index: 974110 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0659. Min Act: -0.1700

Data Index: 646964 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0817. Min Act: -0.1700

Data Index: 141019 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0817. Min Act: -0.1700

Data Index: 272552 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0659. Min Act: -0.1700

Data Index: 58075 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0501. Min Act: -0.1700

Data Index: 580143 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0659. Min Act: -0.1700

Data Index: 912516 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 679642 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1384852 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1371226 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1577546 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1448926 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1577071 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1564824 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1430103 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1391662 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0343. Min Act: -0.1700

Data Index: 227863 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0501. Min Act: -0.1700

Data Index: 1084382 (C4 (Web Text))

Max Activating Token Index: 839