Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1197 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.3303. Min Act: -0.1700

Data Index: 1463256 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.3303. Min Act: -0.1700

Data Index: 1538491 (Python Code)

Max Activating Token Index: 199

Text #2

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2518. Min Act: -0.1700

Data Index: 1562645 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2360. Min Act: -0.1700

Data Index: 1624513 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2203. Min Act: -0.1700

Data Index: 1450757 (Python Code)

Max Activating Token Index: 120

Text #5

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1105497 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2203. Min Act: -0.1700

Data Index: 1625237 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1471560 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2203. Min Act: -0.1700

Data Index: 1425142 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1398766 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1655393 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2046. Min Act: -0.1700

Data Index: 374083 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1377244 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1531064 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1493796 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1508660 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1615462 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1731. Min Act: -0.1700

Data Index: 1466243 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1534013 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 3.3303. Min Range: -3.3303

Max Act: 3.1731. Min Act: -0.1700

Data Index: 1391667 (Python Code)

Max Activating Token Index: 643