Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1975 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.1667. Min Act: -0.1700

Data Index: 1382234 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.1891. Min Act: -0.1700

Data Index: 1495152 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.1150. Min Act: -0.1700

Data Index: 1638655 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.1302. Min Act: -0.1700

Data Index: 1398671 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.1353. Min Act: -0.1700

Data Index: 1499132 (Python Code)

Max Activating Token Index: 913

Text #5

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0996. Min Act: -0.1700

Data Index: 1421197 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0832. Min Act: -0.1700

Data Index: 1654885 (Python Code)

Max Activating Token Index: 997

Text #7

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0924. Min Act: -0.1700

Data Index: 1593803 (Python Code)

Max Activating Token Index: 974

Text #8

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0798. Min Act: -0.1700

Data Index: 1424044 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0719. Min Act: -0.1700

Data Index: 1400934 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0706. Min Act: -0.1700

Data Index: 1633789 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0726. Min Act: -0.1700

Data Index: 1637782 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0769. Min Act: -0.1700

Data Index: 1377099 (Python Code)

Max Activating Token Index: 921

Text #13

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0797. Min Act: -0.1700

Data Index: 1652239 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0752. Min Act: -0.1700

Data Index: 1430032 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0779. Min Act: -0.1700

Data Index: 1491272 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0612. Min Act: -0.1700

Data Index: 1561940 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0458. Min Act: -0.1700

Data Index: 1538600 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0573. Min Act: -0.1700

Data Index: 1497461 (Python Code)

Max Activating Token Index: 845

Text #19

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0653. Min Act: -0.1700

Data Index: 1424179 (Python Code)

Max Activating Token Index: 361