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

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

Neuron 700 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: 5.4924. Min Range: -5.4924

Max Act: 5.4924. Min Act: -0.1700

Data Index: 1538729 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.3987. Min Act: -0.1700

Data Index: 1450172 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.0862. Min Act: -0.1700

Data Index: 1513363 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.2424. Min Act: -0.1700

Data Index: 1427463 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.2112. Min Act: -0.1700

Data Index: 1429798 (Python Code)

Max Activating Token Index: 581

Text #5

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.2112. Min Act: -0.1700

Data Index: 1651770 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.0862. Min Act: -0.1700

Data Index: 1517768 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.1487. Min Act: -0.1700

Data Index: 1428746 (Python Code)

Max Activating Token Index: 277

Text #8

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.0237. Min Act: -0.1700

Data Index: 1561528 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.0862. Min Act: -0.1700

Data Index: 1360012 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.0862. Min Act: -0.1700

Data Index: 1395748 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 5.4924. Min Range: -5.4924

Max Act: 5.0549. Min Act: -0.1700

Data Index: 1534077 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9924. Min Act: -0.1700

Data Index: 1617460 (Python Code)

Max Activating Token Index: 816

Text #13

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9612. Min Act: -0.1700

Data Index: 1413853 (Python Code)

Max Activating Token Index: 203

Text #14

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9612. Min Act: -0.1700

Data Index: 1593226 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9924. Min Act: -0.1700

Data Index: 1424659 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9299. Min Act: -0.1700

Data Index: 1487220 (Python Code)

Max Activating Token Index: 323

Text #17

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9299. Min Act: -0.1700

Data Index: 1484572 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.9299. Min Act: -0.1700

Data Index: 1524594 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 5.4924. Min Range: -5.4924

Max Act: 4.8987. Min Act: -0.1700

Data Index: 1540781 (Python Code)

Max Activating Token Index: 344