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

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

Neuron 982 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: 3.5408. Min Range: -3.5408

Max Act: 3.5408. Min Act: -0.1700

Data Index: 1575105 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.3527. Min Act: -0.1700

Data Index: 1450663 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1544138 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.3213. Min Act: -0.1700

Data Index: 1522655 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.3056. Min Act: -0.1700

Data Index: 1498642 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.2427. Min Act: -0.1700

Data Index: 1635204 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1641. Min Act: -0.1700

Data Index: 1373251 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1641. Min Act: -0.1700

Data Index: 1468357 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1641. Min Act: -0.1700

Data Index: 1465846 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1483. Min Act: -0.1700

Data Index: 1504482 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1483. Min Act: -0.1700

Data Index: 1510313 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1483. Min Act: -0.1698

Data Index: 1471115 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1641. Min Act: -0.1700

Data Index: 1463818 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1483. Min Act: -0.1700

Data Index: 1565774 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1483. Min Act: -0.1700

Data Index: 1574507 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1483. Min Act: -0.1700

Data Index: 1511668 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1457291 (Python Code)

Max Activating Token Index: 836

Text #17

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1466950 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1567538 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 3.5408. Min Range: -3.5408

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1567826 (Python Code)

Max Activating Token Index: 13