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

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

Neuron 1374 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: 5.4952. Min Range: -5.4952

Max Act: 5.4952. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 5.4952. Min Range: -5.4952

Max Act: 5.4327. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 761

Text #2

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.8702. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 817

Text #3

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.8390. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.3702. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.2764. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.2139. Min Act: -0.1700

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.1514. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 5.4952. Min Range: -5.4952

Max Act: 4.1201. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.9795. Min Act: -0.1700

Data Index: 1442105 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.8856. Min Act: -0.1700

Data Index: 1586329 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.8387. Min Act: -0.1700

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.8544. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.8387. Min Act: -0.1700

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.8387. Min Act: -0.1700

Data Index: 1601652 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.7449. Min Act: -0.1700

Data Index: 850529 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.6510. Min Act: -0.1700

Data Index: 1507671 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.6510. Min Act: -0.1700

Data Index: 1438075 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.6510. Min Act: -0.1700

Data Index: 1102188 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 5.4952. Min Range: -5.4952

Max Act: 3.5257. Min Act: -0.1700

Data Index: 1642938 (Python Code)

Max Activating Token Index: 69