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

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

Neuron 821 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: 4.2367. Min Range: -4.2367

Max Act: 4.2367. Min Act: -0.1700

Data Index: 1424043 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.2367. Min Range: -4.2367

Max Act: 4.2367. Min Act: -0.1700

Data Index: 1398385 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.2367. Min Range: -4.2367

Max Act: 4.1742. Min Act: -0.1700

Data Index: 1517420 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.2367. Min Range: -4.2367

Max Act: 4.0804. Min Act: -0.1700

Data Index: 1585283 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 4.2367. Min Range: -4.2367

Max Act: 4.0179. Min Act: -0.1700

Data Index: 1423505 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.9866. Min Act: -0.1700

Data Index: 1400944 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1460499 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1480014 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.9241. Min Act: -0.1700

Data Index: 1379922 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1590592 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8928. Min Act: -0.1700

Data Index: 1401094 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8928. Min Act: -0.1700

Data Index: 1443675 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.9553. Min Act: -0.1700

Data Index: 1634036 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1482885 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8928. Min Act: -0.1700

Data Index: 1541186 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1645116 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1400017 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8302. Min Act: -0.1700

Data Index: 1373834 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.7833. Min Act: -0.1700

Data Index: 1508771 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 4.2367. Min Range: -4.2367

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1621898 (Python Code)

Max Activating Token Index: 1023