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

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

Neuron 1662 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6752. Min Act: -0.1700

Data Index: 1448294 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1533138 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6752. Min Act: -0.1700

Data Index: 1508996 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1568328 (Python Code)

Max Activating Token Index: 901

Text #4

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1558220 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1407043 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1511689 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5813. Min Act: -0.1700

Data Index: 1640976 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5969. Min Act: -0.1700

Data Index: 810045 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1438697 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1465090 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1519577 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1532097 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1430844 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1488147 (Python Code)

Max Activating Token Index: 1010

Text #15

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1464859 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1317631 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1502562 (Python Code)

Max Activating Token Index: 648

Text #18

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1434026 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 3.6752. Min Range: -3.6752

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1552776 (Python Code)

Max Activating Token Index: 698