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

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

Neuron 1943 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: 2.1994. Min Range: -2.1994

Max Act: 2.1994. Min Act: -0.1700

Data Index: 254350 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1828. Min Act: -0.1700

Data Index: 1508680 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1496. Min Act: -0.1700

Data Index: 182111 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1662. Min Act: -0.1699

Data Index: 1407974 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1662. Min Act: -0.1700

Data Index: 1033288 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1329. Min Act: -0.1700

Data Index: 750682 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1329. Min Act: -0.1700

Data Index: 1550317 (Python Code)

Max Activating Token Index: 415

Text #7

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1496. Min Act: -0.1700

Data Index: 1395553 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1700

Data Index: 1363234 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1700

Data Index: 345838 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1699

Data Index: 1533714 (Python Code)

Max Activating Token Index: 538

Text #11

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1700

Data Index: 1424087 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1700

Data Index: 1521031 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.0995. Min Act: -0.1700

Data Index: 1440511 (Python Code)

Max Activating Token Index: 164

Text #14

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1696

Data Index: 1526451 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.0827. Min Act: -0.1700

Data Index: 1463823 (Python Code)

Max Activating Token Index: 626

Text #16

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1699

Data Index: 1606840 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1700

Data Index: 1625072 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1700

Data Index: 1573206 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 2.1994. Min Range: -2.1994

Max Act: 2.1162. Min Act: -0.1699

Data Index: 1398162 (Python Code)

Max Activating Token Index: 843