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

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

Neuron 1935 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: 3.3151. Min Range: -3.3151

Max Act: 3.3151. Min Act: -0.1700

Data Index: 1223027 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1390042 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1428185 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1626175 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1578. Min Act: -0.1700

Data Index: 1541085 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1458833 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1520800 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1551270 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1446958 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1541116 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1492471 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1609495 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1383126 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1592140 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1585221 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1377095 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1263. Min Act: -0.1700

Data Index: 1524603 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1563126 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1505450 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1263. Min Act: -0.1700

Data Index: 1407861 (Python Code)

Max Activating Token Index: 8