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

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

Neuron 1775 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: 3.3182. Min Range: -3.3182

Max Act: 3.3182. Min Act: -0.1700

Data Index: 1636463 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2082. Min Act: -0.1699

Data Index: 1531106 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.2082. Min Act: -0.1700

Data Index: 1655384 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.1452. Min Act: -0.1700

Data Index: 1371462 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.0664. Min Act: -0.1700

Data Index: 1391979 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.0664. Min Act: -0.1700

Data Index: 1447243 (Python Code)

Max Activating Token Index: 93

Text #6

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.0032. Min Act: -0.1700

Data Index: 1560015 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 3.3182. Min Range: -3.3182

Max Act: 3.0032. Min Act: -0.1700

Data Index: 1470222 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9557. Min Act: -0.1700

Data Index: 1489750 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9716. Min Act: -0.1700

Data Index: 1447962 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1561554 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9557. Min Act: -0.1700

Data Index: 1514705 (Python Code)

Max Activating Token Index: 510

Text #12

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1372004 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1583498 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1530934 (Python Code)

Max Activating Token Index: 327

Text #15

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9241. Min Act: -0.1700

Data Index: 1548416 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1421930 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9241. Min Act: -0.1700

Data Index: 1475837 (Python Code)

Max Activating Token Index: 421

Text #18

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9082. Min Act: -0.1694

Data Index: 1517704 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 3.3182. Min Range: -3.3182

Max Act: 2.9082. Min Act: -0.1700

Data Index: 843752 (C4 (Web Text))

Max Activating Token Index: 83