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

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

Neuron 954 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0164. Min Range: -5.0164

Max Act: 5.0164. Min Act: -0.1700

Data Index: 1486862 (Python Code)

Max Activating Token Index: 826

Text #1

Max Range: 5.0164. Min Range: -5.0164

Max Act: 5.0164. Min Act: -0.1700

Data Index: 1595862 (Python Code)

Max Activating Token Index: 986

Text #2

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.9539. Min Act: -0.1700

Data Index: 1559811 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8914. Min Act: -0.1700

Data Index: 1602331 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.9851. Min Act: -0.1700

Data Index: 1517814 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.9539. Min Act: -0.1700

Data Index: 1643290 (Python Code)

Max Activating Token Index: 760

Text #6

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8914. Min Act: -0.1700

Data Index: 1365193 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1549687 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1118351 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7664. Min Act: -0.1700

Data Index: 1649644 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7976. Min Act: -0.1700

Data Index: 1442261 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7976. Min Act: -0.1700

Data Index: 1433580 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7351. Min Act: -0.1700

Data Index: 1462026 (Python Code)

Max Activating Token Index: 167

Text #13

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8289. Min Act: -0.1700

Data Index: 1545968 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7976. Min Act: -0.1700

Data Index: 1474324 (Python Code)

Max Activating Token Index: 244

Text #15

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8289. Min Act: -0.1700

Data Index: 1534486 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8289. Min Act: -0.1700

Data Index: 1368274 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1362274 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7039. Min Act: -0.1700

Data Index: 1602064 (Python Code)

Max Activating Token Index: 890

Text #19

Max Range: 5.0164. Min Range: -5.0164

Max Act: 4.7351. Min Act: -0.1700

Data Index: 1417304 (Python Code)

Max Activating Token Index: 856