Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 843 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1523400 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1681. Min Act: -0.1700

Data Index: 1574831 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1366. Min Act: -0.1700

Data Index: 1445930 (Python Code)

Max Activating Token Index: 526

Text #3

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1612781 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1632997 (Python Code)

Max Activating Token Index: 328

Text #5

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1366. Min Act: -0.1700

Data Index: 1401420 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1500932 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1483144 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1480824 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1430066 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1425439 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1431808 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1645621 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1051. Min Act: -0.1700

Data Index: 1422543 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1373923 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1455949 (Python Code)

Max Activating Token Index: 686

Text #16

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1370739 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1400267 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1466281 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1362423 (Python Code)

Max Activating Token Index: 105